activity
20232026
most citedStreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

Cong Chen, Guo Gan, Kaixiang Ji +7

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overco…

cs.CV2025

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

Zhenyu Yang, Kairui Zhang, Yuhang Hu +7

Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process co…

cs.CV20251 cited

StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA

Yuhang Hu, Zhenyu Yang, Shihan Wang +5

The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Vi…

cs.CV2025

SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models

Zhengxu Tang, Zizheng Wang, Luning Wang +8

Text-to-video (T2V) generation models have made significant progress in creating visually appealing videos. However, they struggle with generating coherent sequential narratives th…

cs.CV2025

SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

Zhenyu Yang, Yuhang Hu, Zemin Du +6

Despite the significant advancements of Large Vision-Language Models (LVLMs) on established benchmarks, there remains a notable gap in suitable evaluation regarding their applicabi…

cs.CV2024

FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior

Zhekai Chen, Wen Wang, Zhen Yang +3

We offer a novel approach to image composition, which integrates multiple input images into a single, coherent image. Rather than concentrating on specific use cases such as appear…