paper-with-me

홈 › Papers

When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

2025-08-21 · Pengcheng Fang, Yuxia Chen, Rui Guo arxiv

Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic reasoning, they remain coarse in temporal perception: timestamps are encoded only implicitly, frame level features are weak in capturing continuity, and language vision alignment often drifts from the entities of interest. In this paper, we present Grounded VideoDiT, a Video LLM designed to overcome these limitations by introducing three key innovations. First, a Diffusion Temporal Latent (DTL) encoder enhances boundary sensitivity and maintains temporal consistency. Second, object grounded representations explicitly bind query entities to localized visual evidence, strengthening alignment. Third, a mixed token scheme with discrete temporal tokens provides explicit timestamp modeling, enabling fine grained temporal reasoning. Together, these designs equip Grounded VideoDiT with robust grounding capabilities, as validated by state of the art results on Charades STA, NExT GQA, and multiple VideoQA benchmarks.

📄 PDF Abstract BibTeX arXiv:2508.15641

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models

2024-10-04 · Haibo Wang, Zhiyang Xu, Yu Cheng, Shizhe Diao 외

Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding. In this paper, we introduce Grounded-…

Dense Video CaptioningSentenceTemporal Sentence GroundingVideo Captioning+1

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format

2024-11-27 · Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang 외

Recent researches on video large language models (VideoLLM) predominantly focus on model architectures and training datasets, leaving the interaction format between the user and the model under-explored. In existing work…

Dense Video CaptioningGrounded Video Question AnsweringHighlight DetectionQuestion Answering+3

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

2026-03-12 · Yiran Guan, Liang Yin, Dingkang Liang, Jianzhong Ju 외 arxiv

Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. Howeve…

Logical ReasoningKnowledge Graphs

TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors

2026-01-06 · Wei-Yuan Cheng, Kai-Po Chang, Chi-Pin Huang, Fu-En Yang 외 arxiv

Dense video captioning aims to interpret and describe all temporally localized events throughout an input video. Recent state-of-the-art methods leverage large language models (LLMs) to provide detailed moment descriptio…

Dense Video CaptioningMoment Retrieval

VideoNorms: Benchmarking Cultural Awareness of Video Language Models

2025-10-09 · Nikhil Reddy Varimalla, Yunfei Xu, Arkadiy Saakyan, Meng Fan Wang 외 arxiv

As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts. To advance cultural norm awareness evaluation in VideoLLMs, we introduce Video…