中文
相关论文

相关论文: E.M.Ground: A Temporal Grounding Vid-LLM with Holi…

200 篇论文

Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread across multiple regions, as in documents and compositional queries. We address this by framing…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Marcel Gröpl , Jaewoo Jung , Seungryong Kim , Marc Pollefeys , Sunghwan Hong

Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Haotong Qin , Cheng Hu , Michele Magno

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D…

计算机视觉与模式识别 · 计算机科学 2023-02-22 Zeyu Xiong , Daizong Liu , Pan Zhou , Jiahao Zhu

Video temporal grounding (VTG) aims to locate precise segments in videos based on language queries, which is a fundamental challenge in video understanding. While recent Multimodal Large Language Models (MLLMs) have shown promise in…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Lu Dong , Haiyu Zhang , Han Lin , Ziang Yan , Xiangyu Zeng , Hongjie Zhang , Yifei Huang , Yi Wang , Zhen-Hua Ling , Limin Wang , Yali Wang

Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present…

计算机视觉与模式识别 · 计算机科学 2026-02-26 Baiqi Li , Kangyi Zhao , Ce Zhang , Chancharik Mitra , Jean de Dieu Nyandwi , Gedas Bertasius

Human action recognition in long-term videos, characterized by complex backgrounds and subtle action differences, poses significant challenges for traditional deep learning models due to computational overhead, difficulty in capturing…

计算机视觉与模式识别 · 计算机科学 2025-08-25 Kaining Li , Shuwei He , Zihan Xu

We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Fufangchen Zhao , Liao Zhang , Daiqi Shi , Yuanjun Gao , Chen Ye , Yang Cai , Jian Gao , Danfeng Yan

How can we perform knowledge reasoning over temporal knowledge graphs (TKGs)? TKGs represent facts about entities and their relations, where each fact is associated with a timestamp. Reasoning over TKGs, i.e., inferring new facts from…

机器学习 · 计算机科学 2022-02-17 Namyong Park , Fuchen Liu , Purvanshi Mehta , Dana Cristofor , Christos Faloutsos , Yuxiao Dong

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…

计算机视觉与模式识别 · 计算机科学 2021-12-24 Dongxu Li , Junnan Li , Hongdong Li , Juan Carlos Niebles , Steven C. H. Hoi

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…

计算机视觉与模式识别 · 计算机科学 2025-12-30 L'ea Dubois , Klaus Schmidt , Chengyu Wang , Ji-Hoon Park , Lin Wang , Santiago Munoz

Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision and language tasks. Several recent works, however, showed…

计算机视觉与模式识别 · 计算机科学 2024-03-07 Navid Rajabi , Jana Kosecka

Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Haibo Wang , Chenghang Lai , Yixuan Sun , Weifeng Ge

Visual Grounding (VG) aims to localize specific objects in an image according to natural language expressions, serving as a fundamental task in vision-language understanding. However, existing VG benchmarks are mostly derived from datasets…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Tianyi Zhao , Jiawen Xi , Linhui Xiao , Junnan Li , Xue Yang , Maoxun Yuan , Xingxing Wei

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic…

计算机视觉与模式识别 · 计算机科学 2019-11-26 Yongfei Liu , Bo Wan , Xiaodan Zhu , Xuming He

Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs)…

计算机视觉与模式识别 · 计算机科学 2026-05-06 Sakshi Agarwal , Aishik Konwer , Ankit Parag Shah

Video-LLMs often attend to irrelevant frames, which is especially detrimental for sports coaching tasks requiring precise temporal grounding. Yet obtaining frame-level supervision is challenging: expensive to collect from humans and…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Arushi Rai , Adriana Kovashka

Video-language models (VLMs) are reshaping video querying services, bringing unified solutions to complex perception and reasoning tasks. However, deploying large VLMs in real-world systems remains challenging due to their high resource…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Miao Zhang , Ruixiao Zhang , Jianxin Shi , Hengzhi Wang , Hao Fang , Jiangchuan Liu

Recognizing and localizing events in videos is a fundamental task for video understanding. Since events may occur in auditory and visual modalities, multimodal detailed perception is essential for complete scene comprehension. Most previous…

计算机视觉与模式识别 · 计算机科学 2022-07-13 Jiashuo Yu , Ying Cheng , Rui-Wei Zhao , Rui Feng , Yuejie Zhang

Video Paragraph Grounding (VPG) aims to precisely locate the most appropriate moments within a video that are relevant to a given textual paragraph query. However, existing methods typically rely on large-scale annotated temporal labels and…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Mengzhao Wang , Huafeng Li , Yafei Zhang , Jinxing Li , Minghong Xie , Dapeng Tao

Event cameras provide a promising sensing modality for high-speed and high-dynamic-range vision by asynchronously capturing brightness changes. A fundamental task in event-based vision is event-to-video (E2V) reconstruction, which aims to…

计算机视觉与模式识别 · 计算机科学 2026-01-08 Jingqian Wu , Yunbo Jia , Shengpeng Xu , Edmund Y. Lam