SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
Videoagent: Long-form video understand- ing with large language model as agent
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
method 1
citation-polarity summary
fields
cs.CV 6representative citing papers
SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.
MLVU is a new benchmark for long video understanding that uses extended videos across diverse genres and multi-task evaluations, revealing that current MLLMs struggle significantly and degrade sharply with longer durations.
VAP is a training-free active-perception method that improves zero-shot long-form video QA performance and frame efficiency up to 5.6x in VLMs by selecting keyframes that differ from priors generated by a text-conditioned video model.
SkillFormer, PATS, and ProfVLM deliver state-of-the-art multi-view proficiency estimation on Ego-Exo4D with up to 20x fewer parameters by combining selective fusion, dense sampling, and generative feedback.
MARS converts long videos to captions and summaries, maintains modality-specific memories, and deploys an agent to select evidence or answer, placing second on the CASTLE Challenge leaderboard.
citing papers explorer
-
SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
-
Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.
-
MLVU: Benchmarking Multi-task Long Video Understanding
MLVU is a new benchmark for long video understanding that uses extended videos across diverse genres and multi-task evaluations, revealing that current MLLMs struggle significantly and degrade sharply with longer durations.
-
Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models
VAP is a training-free active-perception method that improves zero-shot long-form video QA performance and frame efficiency up to 5.6x in VLMs by selecting keyframes that differ from priors generated by a text-conditioned video model.
-
Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback
SkillFormer, PATS, and ProfVLM deliver state-of-the-art multi-view proficiency estimation on Ego-Exo4D with up to 20x fewer parameters by combining selective fusion, dense sampling, and generative feedback.
-
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
MARS converts long videos to captions and summaries, maintains modality-specific memories, and deploys an agent to select evidence or answer, placing second on the CASTLE Challenge leaderboard.