会员服务
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
Arxiv
0+阅读 · 2月18日
AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured Reasoning
Arxiv
0+阅读 · 2月7日
CauCLIP: Bridging the Sim-to-Real Gap in Surgical Video Understanding via Causality-Inspired Vision-Language Modeling
Arxiv
0+阅读 · 2月6日
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
Arxiv
0+阅读 · 2月8日
State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models
Arxiv
0+阅读 · 2月7日
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
Arxiv
0+阅读 · 2月9日
Active Perception Agent for Omnimodal Audio-Video Understanding
Arxiv
0+阅读 · 2月5日
TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?
Arxiv
0+阅读 · 2月5日
VideoNSA: Native Sparse Attention Scales Video Understanding
Arxiv
0+阅读 · 1月30日
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
Arxiv
0+阅读 · 2月3日
FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO
Arxiv
0+阅读 · 1月30日
Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
Arxiv
0+阅读 · 2月2日
FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
Arxiv
0+阅读 · 2月2日
KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
Arxiv
0+阅读 · 2月3日
VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
Arxiv
0+阅读 · 1月25日
参考链接
微信扫码咨询专知VIP会员
Top