English
Related papers

Related papers: SPARROW: Learning Spatial Precision and Temporal R…

200 papers

In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Andong Deng , Tongjia Chen , Shoubin Yu , Taojiannan Yang , Lincoln Spencer , Yapeng Tian , Ajmal Saeed Mian , Mohit Bansal , Chen Chen

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Haiyi Qiu , Minghe Gao , Long Qian , Kaihang Pan , Qifan Yu , Juncheng Li , Wenjie Wang , Siliang Tang , Yueting Zhuang , Tat-Seng Chua

Temporal grounding aims to locate a target video moment that semantically corresponds to the given sentence query in an untrimmed video. However, recent works find that existing methods suffer a severe temporal bias problem. These methods…

Computer Vision and Pattern Recognition · Computer Science 2022-08-08 Jiachang Hao , Haifeng Sun , Pengfei Ren , Jingyu Wang , Qi Qi , Jianxin Liao

Although speculative decoding is widely used to accelerate Vision-Language Models (VLMs) inference, it faces severe performance collapse when applied to Video Large Language Models (Vid-LLMs). The draft model typically falls into the trap…

Computer Vision and Pattern Recognition · Computer Science 2026-02-18 Libo Zhang , Zhaoning Zhang , Wangyang Hong , Peng Qiao , Dongsheng Li

Spatio-temporal video grounding (STVG) aims at localizing the spatio-temporal tube of a video, as specified by the input text query. In this paper, we utilize multimodal large language models (MLLMs) to explore a zero-shot solution in STVG.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Zaiquan Yang , Yuhao Liu , Gerhard Hancke , Rynson W. H. Lau

Spatio-Temporal Video Grounding requires jointly localizing target objects across both temporal and spatial dimensions based on natural language queries, posing fundamental challenges for existing Multimodal Large Language Models (MLLMs).…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Xuezhen Tu , Jingyu Wu , Fangyu Kang , Qingpeng Nong , Kaijin Zhang , Chaoyue Niu , Fan Wu

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities across a wide range of vision-language tasks. However, due to the restricted input resolutions, MLLMs face significant challenges in precisely understanding and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Lu Zhang , Jiazuo Yu , Haomiao Xiong , Ping Hu , Yunzhi Zhuge , Huchuan Lu , You He

Referring Video Object Segmentation (RefVOS) seeks to segment target objects in videos guided by natural language descriptions, demanding both temporal reasoning and fine-grained visual comprehension. Existing sampling strategies for…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Ming Dai , Sen Yang , Boqiang Duan , Wankou Yang , Jingdong Wang

Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Xin Li , Deshui Miao , Zhenyu He , Yaowei Wang , Huchuan Lu , Ming-Hsuan Yang

Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Zijia Lu , Jingru Yi , Jue Wang , Yuxiao Chen , Junwen Chen , Xinyu Li , Davide Modolo

Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Jihwan Hong , Jaeyoung Do

Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Wei Wang , Yuqian Yuan , Tianwei Lin , Wenqiao Zhang , Siliang Tang , Jun Xiao , Yueting Zhuang

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Henghao Zhao , Ge-Peng Ji , Rui Yan , Huan Xiong , Zechao Li

Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jiangyang Li , Cong Wan , Changjie Wu , Songlin Dong , Lingjun Zhang , Linzhe Shi , Xu Wang , Zhiheng Ma , Hang Zhang , Mu Xu , Yihong Gong

The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Jingnan Luo , Mingqi Gao , Jun Liu , Bin-Bin Gao , Feng Zheng

Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Niccolo Avogaro , Nayanika Debnath , Li Mi , Thomas Frick , Junling Wang , Zexue He , Hang Hua , Konrad Schindler , Mattia Rigotti

Semantic segmentation networks adopt transfer learning from image classification networks which occurs a shortage of spatial context information. For this reason, we propose Spatial Context Memoization (SpaM), a bypassing branch for spatial…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Taehun Kim , Jinseong Kim , Daijin Kim

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Diankun Wu , Fangfu Liu , Yi-Hsin Hung , Yueqi Duan

Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Xinhao Li , Ziang Yan , Desen Meng , Lu Dong , Xiangyu Zeng , Yinan He , Yali Wang , Yu Qiao , Yi Wang , Limin Wang

Multimodal large language models (MLLMs) have achieved remarkable progress across a range of vision-language tasks and demonstrate strong potential for traffic accident understanding. However, existing MLLMs in this domain primarily focus…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Zihao Sheng , Zilin Huang , Yansong Qu , Jiancong Chen , Yuhao Luo , Yen-Jung Chen , Yue Leng , Sikai Chen