Video_Caption
-
EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding
2026-07-29 06:33:11Yuyun Chen, Tianao Li, TianQuan Feng, Cen Chen, Huiping Zhuang, Hao Peng, Ziqian ZengAbstract
Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic uncertainty. While Large Vision-Language Models (LVLMs) demonstrate impressive semantic alignment on standard benchmarks, they often struggle to distinguish between superficial correlation and genuine forensic logic when grounded in the dynamic, partially observable nature of first-person experiences. Existing evaluations, dominated by third-person surveillance footage and binary classification metrics, fail to expose this cognitive gap. To address this, we introduce EgoSafe-Bench, a benchmark specifically designed to probe forensic reasoning in egocentric safety scenarios. It comprises 12,000 unique evaluation samples, generated by pairing each of the 3,000 video clips with a QA chain governed by our proposed Hierarchical Reasoning Evaluation (HRE) protocol. Unlike standard benchmarks, HRE mandates a rigorous reasoning trajectory from initial feature anchoring to blind-spot deduction and intent inference, thereby enforcing logical consistency and penalizing shortcut-based this http URL evaluations of state-of-the-art LVLMs (e.g., Qwen3-VL, Gemini, VideoLLaMA 3) reveal a significant perception-reasoning decoupling: models often achieve high descriptive scores but exhibit notable fragility in causal reasoning and logical closure. Our work provides both a challenging dataset and a systematic evaluation framework to foster the development of logically robust video understanding systems.
Abstract (translated)
URL
https://arxiv.org/abs/2607.26518
PDF
-
RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection
2026-07-28 07:54:03Tianyu Li, Jiahao He, Keren Fu, Qijun ZhaoAbstract
We introduce RDVSv2, a large-scale benchmark for RGB-D video salient object detection (RGB-D VSOD) with dense frame-level annotations. Existing datasets in this emerging field are often limited in scale and annotation quality, while also relying on less geometry-consistent depth cues. To address these limitations, RDVSv2 is built from publicly accessible stereoscopic online videos and contains 249 video sequences with 29,077 annotated frames. It includes depth maps derived from stereoscopic videos, together with frame-wise salient object masks annotated with eye-tracking guidance. Compared with existing datasets, RDVSv2 is much larger in scale and covers more diverse and challenging scenarios. In addition, we establish a strong baseline for RGB-D VSOD based on Segment Anything Model 2 (SAM2). Specifically, we employ a parameter-efficient fine-tuning (PEFT) strategy to adapt the SAM2 encoder to jointly encode RGB, depth, and optical flow cues. Extensive experiments show that RDVSv2 is substantially more challenging for existing RGB-D VSOD methods. Meanwhile, the proposed baseline achieves state-of-the-art results on RDVSv2 and existing RGB-D VSOD benchmarks. We hope that RDVSv2 and the provided baseline will serve as useful resources for future research on RGB-D VSOD and related multi-modal video understanding tasks. Our dataset and code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25392
PDF
-
FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding
2026-07-28 04:09:49Ghazal Kaviani, Ghassan AlRegibAbstract
Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of relevant content decreases sharply as video sequence length increases, and exposing the model to more irrelevant content measurably reduces its accuracy. In this paper, we address the problem of maximizing query-relevant information in a frame subset selected at inference time, without training. FORGE (Frame Orthogonality in Relevance Geometry) is a model-agnostic method that induces a query-conditioned geometry on a pretrained multimodal embedding space, unifying relevance and diversity into a single objective. In this space, frames that cover independent query-relevant directions are far apart, and selecting the subset of maximum information captures diverse query-relevant content within the budget. Experiments on Video-MME and LongVideoBench at budgets of 16, 32, and 64 frames show that FORGE improves the unified keyframe selection score by 11.0-15.3 points over the strongest training-free baseline and up to doubles keyframe recall (0.415 vs. 0.204 at K=64 on Video-MME). The gains extend to question answering, where accuracy improves in every evaluated setting across eight open-source MLLMs spanning 4B to 32B parameters, by up to 8.7 points over uniform sampling and 5.2 points over the strongest baseline. Our findings suggest that aligning the embedding space with the query's high-dimensional structure is a promising direction for inference-time video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25266
PDF
-
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
2026-07-27 17:59:53Senqiao Yang, Kaichen Zhang, Zhaoyang Jia, Jinghao Guo, Yifei Shen, Xinjie Zhang, Xiaoyi Zhang, Haoqing Wang, Xiao Li, Peng Zhang, Xiang An, Yin Xie, Zhening Liu, Xun Guo, Jiahao Li, Shicheng Zheng, Jinglu Wang, Zongyu Guo, Wenxuan Xie, Zihan Zheng, Yuxuan Luo, Bin Li, Yan LuAbstract
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process them inefficiently. We present Mage-VL, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction. At its core, our custom tokenizer, Mage-ViT, replaces uniform frame sampling by selectively encoding dynamic, entropy-rich regions using motion vectors and residual energy across sparse anchor (I) and predicted (P) frames. Operating at a 16 x 16 patch level, this reduces visual token consumption by over 75% while preserving spatiotemporal context. Trained from scratch on approximately 560M unlabeled images and 100M unlabeled video frames, Mage-ViT matches or outperforms flagship encoders trained on billions of image-text pairs. We establish AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes. Furthermore, through a bio-inspired dual-system architecture - a lightweight System 1 event gate and a causal System 2 decoder - Mage-VL enables proactive streaming perception. Extensive evaluations show that Mage-VL-4B matches Qwen3-VL-4B on static tasks while achieving strong gains in video understanding and 2D/3D spatial reasoning, with up to a 3.5x wall-clock inference speedup, and comprehensively surpasses the 15B Phi-4-reasoning-vision baseline. Beyond model artifacts, we deliver seven key empirical findings covering pre-training data efficiency, variable-resolution scaling, codec system acceleration, VideoQA SFT redundancy, motion-spatial synergy, AI4AI data pipelines, and Zero-Vision SFT for multimodal RL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.24904
PDF
-
CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
2026-07-27 15:49:42Jinlong Yang, Wenhao Zhang, Kuanwei Lin, Sijie ChengAbstract
Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example regardless of difficulty. This uniform strategy invokes unnecessary tool-assisted processing for easy questions and provides limited control when difficult questions require fine-grained temporal evidence. We propose CADER (Confidence-Aware Dynamic Evidence Reasoning), a training-free framework for adaptive and reliable long-video reasoning. CADER first performs global reasoning over uniformly sampled frames and estimates answer confidence with a logit-margin signal, allowing high-confidence examples to exit early. For uncertain examples, CADER activates a second-stage tool-augmented loop that combines temporal cropping, lightweight semantic verification, and Relevance-Guided Resampling to progressively localize question-relevant evidence. This design treats tool use as a sample-level decision: a single global pass handles easy cases, while additional reasoning is reserved for examples where uncertainty suggests that more evidence is needed. Experiments on multiple VideoQA benchmarks show that CADER improves long-video reasoning while bypassing Stage~2 for high-confidence samples. Moreover, when applied to a backbone trained only with tool-free chain-of-thought supervision, CADER achieves competitive performance against specialized tool-augmented frameworks, suggesting a practical inference-time route for adaptive long-video reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2607.24582
PDF
-
MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning
2026-07-27 07:06:14Tuan-An To, Yuk-Kwan Wong, Tuan-Anh Vu, Ziqiang Zheng, Sai-Kit YeungAbstract
Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality image-text pairs. However, the performance of VLMs often degrades in the video domain due to the essential need for temporal understanding and the scarcity of large-scale annotated video data. In this work, we focus on marine video understanding, which brings further challenges: first, it requires substantial domain expertise; and video VLMs usually struggle with localizing and interpreting critical information from marine videos, as the informative events are typically sparse, unpredictable, and unevenly distributed. To address these challenges, we carefully curate the first event-centric marine video understanding dataset called MarineEVT, which features 20K multi-task, video-level visual question-answering pairs spanning multiple dimensions of marine understanding and analysis. Meanwhile, based on MarineEVT, we decompose marine video understanding as an Event-centric Visual Tool-integrated Reasoning process EVT-R1 for short, where we leverage powerful visual tools to drive the model to localize and interpret critical information aligned with visual questions and human intent. To demonstrate its effectiveness, we compare EVT-R1 against 11 SOTA VLMs in different settings. EVT-R1 outperforms the top open-source and top commercial models by 5.22 and 11.09, respectively. MarineEVT and EVT-R1 lay the foundation for ecological discovery and marine education, fostering the development of VLMs capable of interpreting marine dynamics, reasoning about ecological interactions, and supporting sustainable ocean video understanding and analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2607.24064
PDF
-
WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
2026-07-25 16:05:22Yuhui Zeng, Wang Chen, Jinfa Huang, Tianyu Xie, Yongdong Luo, Jiayi Ji, Xiawu Zheng, jiebo LuoAbstract
Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. While recent efficient methods attempt to compress tokens via hard pruning or uniform merging, they operate strictly in the spatial feature domain, where robust structural context and discriminative semantic details are inherently entangled. In this work, we propose WaveZip, a joint signal-frequency-domain framework for efficient video inference. Driven by the insight that temporal redundancy resides in low-pass approximation scales while spatial saliency strongly correlates with high-frequency components, WaveZip leverages Discrete Wavelet Transforms (DWT) to disentangle these signals. Temporally, it employs 1D DWT to analyze query-frame relevance, and the resulting high-frequency coefficients are further gated by inter-frame differences, with both signals jointly driving the dynamic allocation of a precise frame-level token budget. Spatially, a 2D DWT decomposes features into low-frequency approximations and high-frequency detail components, where the high-frequency coefficients are modulated within query-salient regions to regulate spatial reconstruction. Importantly, WaveZip requires no task-specific training and can be seamlessly integrated into off-the-shelf LVLMs to boost inference efficiency. Extensive experiments on long video understanding benchmarks demonstrate that WaveZip retains 99.6% of the full performance under an extreme 10x compression ratio, consistently outperforming state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2607.23265
PDF
-
BasketEvent: Understanding Who Did What and When in Basketball Videos
2026-07-23 12:39:56Yu Zhang, Jiayuan Rao, Haoning Wu, Weidi XieAbstract
Comprehensive basketball video understanding requires resolving not only what event occurs, but also who is responsible and when the key evidence appears. However, exist- ing methods typically treat spatial perception and semantic recognition as isolated tasks, failing to ground events to individual players or pinpoint their temporal boundaries within complex collective dynamics. To bridge this gap, we introduce BasketEvent, a player- centric basketball event understanding dataset curated from real NBA broadcasts. In BasketEvent, event labels are grounded to the responsible players, and a manually an- notated subset of 1,000 samples with precise event intervals is provided to evaluate tem- poral evidence localization. Based on this data, we propose PlayNet, a player-centric reasoning framework that maps basketball videos to player-level event predictions with temporal evidence. Concretely, PlayNet tracks key entities, associates player identities, and reasons about events by modeling player-player, player-ball, and global court inter- actions, while aggregating sparse temporal evidence via gated pooling. Extensive experi- ments demonstrate that PlayNet significantly outperforms representative video-level and crop-based baselines, proving the superiority of player-centric modeling for fine-grained sports video understanding. Our data, code, and models will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21267
PDF
-
T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video
2026-07-23 11:44:11Linlin Wang, Xue Yang, Zhihuang Zhou, Zhenyu Zhong, Ruiyuan Zhang, Yansheng LiAbstract
Structured understanding of satellite video is essential for advancing dynamic geospatial scene analysis from low-level perception to high-level cognition. To move beyond object-centric perception, this paper introduces spatio-temporal panoptic scene graph generation (TPSG) in satellite video as a new benchmark task. TPSG aims to generate a structured graph composed of a set of triplets <subject, relationship, object> with explicit temporal spans, thereby describing dynamic geospatial scenes by jointly modeling identity-consistent instance masks and spatio-temporal relationships among panoptic scene elements. However, there is still no dedicated dataset for TPSG in satellite video. Moreover, TPSG in satellite video is intrinsically challenging, as objects are often small and weakly textured, cross-frame association is easily disrupted by occlusion and background clutter, and relationship semantics are highly coupled with spatial structure and temporal evolution. Consequently, TPSG models developed for natural videos are not directly applicable to satellite video. This paper presents T-STAR, a large-scale benchmark dataset for TPSG in satellite video, comprising over 1.1 million instance masks and over 3.8 million spatio-temporal triplets across 39 fine-grained object categories and 70 fine-grained relationship categories. To enable TPSG in satellite video, we propose a unified framework to enhance cross-frame instance consistency and spatio-temporal relationship prediction. Extensive experiments demonstrate the significance of T-STAR and the effectiveness of the proposed framework, establishing a strong benchmark for future research on structured satellite video understanding. The dataset and code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21228
PDF
-
ProCap: Prominence-guided Object Rectification for Faithful and Comprehensive Video Captioning
2026-07-23 08:06:55Debjyoti Das Adhikary, Aritra Hazra, Partha Pratim ChakrabartiAbstract
Improving video captioning quality typically demands retraining large vision-language models, an expensive and often impractical requirement. Existing training-free alternatives instead ground captions in detected objects to curb hallucination, but apply only a single, fixed correction pass without prioritizing which objects matter most, leaving semantically significant content omitted. We propose a prominence-aware, iterative post-hoc rectification framework that overcomes both limitations without modifying the underlying captioning model's parameters: a lightweight scoring mechanism ranks detected objects by spatial saliency, temporal persistence, and relational dynamics, and an iterative, prompt-driven refinement loop uses this ranking to progressively inject missing yet contextually relevant objects into the caption over multiple rounds. We validate the framework on MSVD and MSR-VTT using object-grounded automatic metrics, a 110-participant human study, and qualitative comparison against ChatGPT and Gemini; in human evaluation, the framework raises perceived completeness by up to 48% and reduces hallucination by up to 45% relative to a strong pretrained captioning baseline, all without retraining or reference captions. These results position prominence-guided iterative rectification as a lightweight, scalable, and model-agnostic route to more complete and trustworthy video captioning, with direct relevance to accessibility, retrieval, and other multimedia understanding applications.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21022
PDF
-
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization
2026-07-23 07:52:40Lihuang Fang, Yuchen Zou, kebin Jin, Jinghui QinAbstract
Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new level that is complex emotion understanding with advanced video understanding abilities and natural language description. However, existing MLLM-based methods often use a fixed prompt to perceive the emotions, ignoring the dynamicity and complexity of the emotion source in the multimodal inputs. To address these issues, we propose a novel Reinforcement Learning-based Dynamic Agent Specialization framework (\textbf{EmoAgent-R1}) to optimize the emotion recognition, reasoning, and generalization abilities of an MLLM with dynamic agent specialization based on reinforcement learning. Specifically, we first adopt a cold start strategy to endow an MLLM with preliminary emotion recognition, reasoning, and agent routing ability by training with synthetic answer-conditioned chain-of-thought data and agent routing data. Then, we further train the MLLM with reinforcement learning to perceive emotions in a two-step agentic workflow with agent selection and agent specialization. To effectively train EmoAgent-R1, we propose a novel Progressive Group-Relative Policy Optimization (P-GRPO) to combine group-based relative advantages with a PMI-inspired progressive token-level modulation to transform sparse rewards into fine-grained learning signals, mitigating the coarse-grained uniform credit assignment issue in GRPO. Extensive experiments on MER benchmarks demonstrate the superiority of our EmoAgent-R1 in stronger emotion reasoning performance and improved optimization stability.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21013
PDF
-
ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?
2026-07-23 02:49:24Han Li, Si Liu, Zehao Huang, Dongxin Lyu, Longfei Xu, Jiahui Fu, Daxin Tian, Yuliang Xiu, Naiyan WangAbstract
Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse expert-level tasks, but they still struggle with fundamental abilities that humans naturally develop through continuous observation of the real world, such as spatial perception and dynamic reasoning. Recent studies have recognized this gap and introduced dedicated benchmarks to evaluate the spatial-temporal capabilities of MLLMs. However, existing benchmarks mostly focus on static scenes or require exact quantitative predictions, leaving intuitive reasoning from temporal cues largely underexplored. In this paper, we introduce the Visual Spatial-Temporal Reasoning Benchmark (ViSTR-Bench), a novel evaluation suite designed to systematically assess whether MLLMs can perform qualitative reasoning from continuous visual cues in dynamic scenes. Guided by the principles of temporal emphasis, reasoning orientation, and qualitative evaluation, ViSTR-Bench establishes a comprehensive four-dimensional evaluations covering Motion Perception, Spatial Relations, Outcome Prediction, and Physical Dynamics. The benchmark comprises 15 distinct subtasks and 1,340 high-quality video question-answer pairs spanning diverse tabletop, indoor, and outdoor scenarios. Extensive evaluations of a broad spectrum of state-of-the-art proprietary, open-source, and specialized spatial MLLMs reveal that, despite their strong general video understanding capabilities, current models still face substantial bottlenecks in complex spatial-temporal reasoning and remain far below human performance.
Abstract (translated)
URL
https://arxiv.org/abs/2607.20868
PDF
-
PercepCap: Video Captioner with Structured Spatio-Temporal Perception
2026-07-22 17:17:33Yifan Xu, Zihao Wang, Zhixiao Wang, Jiaming Zhang, Yichun Yang, Desen Meng, Yuanxing Zhang, Pengfei Wan, Limin WangAbstract
Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without exposing the perceptual evidence behind descriptions. As a result, mistakes in spatiotemporal perception are only observed in the final caption, making it difficult to identify the underlying perceptual errors directly. To address these issues, we present PercepCap, a perception-aware video captioning framework that makes perceptual evidence explicit before producing the final caption. Specifically, PercepCap follows a perceive-describe generation chain, where the model first produces a spatiotemporal perception trace comprising object trajectories and temporal events, and then generates the final caption conditioned on the perceived evidence. To support this, we design a two-stage training strategy. Perceive-then-Describe Supervised Fine-tuning adapts the model from caption-only generation to the proposed perceive-describe chain, while Perception-Grounded Reinforcement Learning optimizes perception trace and caption quality with joint rewards over perception chain and the final caption. To support our two-stage training, we introduce Caption-Anchored Perception Data Construction. This pipeline builds the SFT and RL training data by first generating a caption-only description, extracting the objects and events it mentions, and grounding them back in the video with boxes and timestamps. This yields caption-aligned perception data that provides solid training ground truth, ensuring that the explicit perception trace and final caption refer to the same objects and events. Across direct caption and caption-to-QA evaluation, PercepCap consistently improves upon the Qwen3-VL baseline and demonstrates leading caption quality.
Abstract (translated)
URL
https://arxiv.org/abs/2607.20389
PDF
-
PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models
2026-07-22 05:17:38Zihan Song, Shuo Ye, Bo Zhao, Ruixin Zhang, Jiayu Zhang, Shouhong Ding, Zitong YuAbstract
Despite advances in Video Large Language Models (VLLMs) that have displayed promising outcomes in video understanding, the redundancy in the long-duration frames remains a hindrance to efficient reasoning. This paper introduces a training-free $\mathbf{P}$ersistence-Aware $\mathbf{C}$ompression and $\mathbf{A}$ggregation (PCA) method designed to preserve high-fidelity raw visual information before the encoding stage. PCA can be built on arbitrary VLLMs and consists of two modules: 1) A Dynamic Downsampling (DD) module that adaptively removes redundant frames by analyzing frame-wise similarity. 2) A Persistence-Aware Motion Enhancement (PAME) module that enriches each selected keyframe by aggregating the temporal context of its neighbors, ensuring that essential information is preserved even after aggressive frame reduction. Our approach substantially reduces the computation of long-context modeling, while enhancing the performance of the baseline model. Extensive experiments demonstrate that PCA consistently outperforms existing state-of-the-art approaches in both efficiency and accuracy, achieving a speedup of 1.8$\times$ to 2.5$\times$ compared to the baseline VLLM. The code is open-sourced at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.22726
PDF
-
BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics
2026-07-21 19:00:32Shubham Baid, Akash James, Sahil Chachra, Nishant Sinha, Kunal KislayAbstract
Continuous surveillance video creates a growing storage, transmission, and inference burden for enterprise video analytics systems. While modern codecs such as H.265 reduce bitrate for human-viewable video, aggressive compression can degrade downstream computer-vision performance and does not necessarily reduce the number of vision-language model (VLM) inference calls required for semantic video understanding. This paper evaluates BLUE, a fixed-camera surveillance compression approach that suppresses static-background redundancy while preserving foreground activity, for its effect on VLM-based event and anomaly understanding. We compare raw H.265 and BLUE-compressed H.265 video on two surveillance datasets: VIRAT, comprising 227 paired event samples from 106 clips, and CHAD, comprising 54 human-activity anomaly clips. For each pair, the same frame index is evaluated using a VLM captioning pipeline, and outputs are scored against annotation-derived ground truth using a blind judging protocol. The results show no measurable degradation in semantic inference quality. On VIRAT, the mean VLM score remains effectively unchanged between raw H.265 and BLUE, with a mean difference of approximately -0.01 on a 0-10 scale. On CHAD, raw H.265 and BLUE obtain near-equivalent mean scores of 4.31 and 4.26, respectively. Compression saving is also uncorrelated with VLM score change on VIRAT (r = 0.004), indicating that higher BLUE compression does not predict semantic quality loss. Beyond storage reduction, BLUE increases the share of skip-heavy P-frames on CHAD from 1.4% to 53.2%, enabling an estimated 53% reduction in VLM calls through packet-size-based frame skipping. These findings suggest that BLUE functions as a machine-centric compression layer for surveillance video, reducing bandwidth and inference cost while preserving VLM semantic performance.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19515
PDF
-
Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation
2026-07-21 07:07:19Amber Yijia Zheng, Lu Liu, Raymond A. Yeh, Xi YinAbstract
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often underexplored. Real-world data curation is complex and non-trivial, involving clip selection from raw videos and captioning to create video-text pairs for learning text-to-video mappings. We study how data distribution and caption quality impact text-to-video models. To enable controlled experiments, we introduce Moving Alphabet, a procedural testbed that renders letters with varying fonts, colors, sizes, and positions, moving in different directions and speeds against a black background. This design allows precise control over data distribution and caption quality by corrupting ground-truth metadata. Our experiments yield three findings: a) a diverse and balanced distribution of video content and duration is critical for generalization; b) caption quality significantly affects both model performance and training efficiency, suggesting that text-to-video models are bounded by video understanding capabilities; and c) classifier-free guidance and fine-tuning on high-quality data provide partial recovery from models trained on corrupted captions, but cannot fully compensate for poor pre-training data. We believe these insights can inform the development of large-scale text-to-video models, and we advocate for greater attention to the science of pre-training data.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18789
PDF
-
Continual Video-MLLM Adaptation over Evolving Domains
2026-07-21 05:16:36Rui Cheng, Meixing Shi, Yuxiang Cai, Jingcai Guo, Jianwei Yin, Zhi ChenAbstract
Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains. DAER maintains domain-isolated lightweight experts while keeping the pretrained Video-MLLM backbone frozen, thereby decoupling domain-specific adaptation from the general multimodal knowledge of the pretrained model. To enable fine-grained specialization, we introduce an intra-domain distribution-aware routing mechanism that matches each input to expert-level prototype reservoirs using MMD. To address the absence of task identities at inference time, we further propose an inter-domain routing mechanism that performs prototype matching in a discriminative subspace for robust domain identification. In addition, we introduce adaptive domain merging to improve parameter scalability and adopt a two-stage optimization strategy to stabilize expert specialization during continual learning. We evaluate DAER by curating a domain-incremental benchmark built from ten VidQA datasets covering diverse visual environments and reasoning demands. Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18716
PDF
-
HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization
2026-07-20 14:27:06Rui Chu, Yingjie LaoAbstract
Video understanding has become more and more important with the growth of Artificial Intelligence (AI) for video generation. Recently, Multimodal Large Language Model(M-LLM) has shown its capability in video understanding. Video summarization, a specific domain of video understanding, has proven its importance for efficient navigation and retrieval. Both video understanding and video summarization require a good selection of key frames in a video. Current video summarization methods heavily focus on the selected key frames and correlated segment captions. However, existing approaches overlook the perspective of treating the importance of the frames globally. We argue that using discrete selected frames for summarization will not only reduce the understanding coherence, but also lost important information in the video, as well as wasting the original capacity of the MLLMs. In this paper, we propose HAS, a Highlight-guided Attention Steering method for video summarization. We consider a challenging but practical setting where the video given to MLLMs for summarize should be continuous but with highlight guidance. HAS mainly consists of two parts: The first part is to find a continuous frame-level highlight distribution for the video globally. The second part is to apply the highlight distribution as an attention steering vector for the MLLM, targeting a better understanding of the video, and thus during the model inference time, putting more attention on the highlighted frames, while avoiding lost entire information on less highlighted frames through putting less attention instead of forgetting them. We evaluated HAS on a variety of benchmarks, and it has shown convincing performance in video summarization.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17994
PDF
-
Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection
2026-07-20 07:30:16Amir Hosein Fadaei, Mahyar Maleki, Mohammad-Reza A. DehaqaniAbstract
Modern video transformers typically ignore principles from primate vision and are rarely evaluated against neural data, limiting their biological interpretability. We introduce a sparse winner-takes-all token selection module that replaces dense self-attention to improve efficiency and approximate competitive routing observed in biological visual circuits. We further propose a neuro-inspired split-and-fuse video transformer which uses two complementary pathways: a high-resolution, low-frame-rate "what" stream and a low-resolution, high-frame-rate "where" stream, fused before classification. On Kinetics-400 and Something-Something V2, our best variant operates on the Pareto frontier of accuracy versus inference time among models of comparable scale and pretraining, and showing improved robustness to spatial perturbations. Using representational similarity analysis between model embeddings and time-resolved EEG recordings for the same video stimuli, our model attains a peak brain-model correlation of 0.18 (about 78% of the noise ceiling) and consistently outperforms strong video transformer baselines, suggesting that pathway specialization and sparse competition are useful inductive biases for efficient, brain-aligned video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17625
PDF
-
SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing
2026-07-19 19:07:19Kaiwen Jing, Ruixu Jia, Bingyao Li, Ruizhe Ou, Ming Wu, Chuang ZhangAbstract
Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved remote sensing (RS) multimodal understanding. Language-conditioned segmentation is crucial for fine-grained target understanding in Unmanned Aerial Vehicle (UAV) videos. However, this task remains challenging due to the prevalence of small, visually ambiguous targets and dynamic aerial perspectives. In this paper, we propose SkyVLaM, a multimodal large language model for UAV video understanding. SkyVLaM constructs sparse tokens directly from patch-level video representations through a temporal basis perceiver, regularizes the sparse basis to encourage complementary temporal cues, and adaptively selects a temporally coherent dense segment for high-resolution inspection. The resulting sparse and dense tokens are jointly processed by a large language model for query-conditioned segmentation. We further build SkyVid, consisting of SkyVid-VGCG and SkyVid-RVOS for video grounded conversation generation and referring video object segmentation, respectively. SkyVid contains 101 videos, 33.6K frames, and 1.53M pixel-level object instances. Experiments show that SkyVLaM provides a more effective allocation of the visual token budget and improves language-conditioned video segmentation in UAV scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17386
PDF
