English
Related papers

Related papers: Grounding Physical Concepts of Objects and Events …

200 papers

Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, current multimodal large language models (MLLMs) cannot do this,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Wenxin Ma , Chenlong Wang , Ruisheng Yuan , Hao Chen , Nanru Dai , S. Kevin Zhou , Yijun Yang , Alan Yuille , Jieneng Chen

Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zongxin Yang , Guikun Chen , Xiaodi Li , Wenguan Wang , Yi Yang

A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Vision-Language Models (VLMs), when applied as driving…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Chun-Peng Chang , Chen-Yu Wang , Holger Caesar , Alain Pagani

Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Junjie Wang , Keyu Chen , Yulin Li , Bin Chen , Hengshuang Zhao , Xiaojuan Qi , Zhuotao Tian

In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains opaque. While Chain-of-Thought prompting is widely used,…

Artificial Intelligence · Computer Science 2026-05-28 Carmen Quiles-Ramírez , Leticia L. Rodríguez , Nicolás Martorell , Natalia Díaz-Rodríguez

Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Linhui Xiao , Xiaoshan Yang , Xiangyuan Lan , Yaowei Wang , Changsheng Xu

Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). However, this adaptation remains challenging, as it requires…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Yiyang Huang , Yizhou Wang , Yun Fu

Combining gradient-based trajectory optimization with differentiable physics simulation is an efficient technique for solving soft-body manipulation problems. Using a well-crafted optimization objective, the solver can quickly converge onto…

Machine Learning · Computer Science 2023-12-12 Zhiao Huang , Feng Chen , Yewen Pu , Chunru Lin , Hao Su , Chuang Gan

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Changpeng Wang , Haozhe Wang , Xi Chen , Junhan Liu , Taofeng Xue , Chong Peng , Donglian Qi , Fangzhen Lin , Yunfeng Yan

Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Yuhang Zang , Wei Li , Jun Han , Kaiyang Zhou , Chen Change Loy

Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition…

Computer Vision and Pattern Recognition · Computer Science 2015-05-05 Xiaodan Liang , Si Liu , Yunchao Wei , Luoqi Liu , Liang Lin , Shuicheng Yan

Recent advances in Artificial Intelligence (AI) technology have promoted their use in almost every field. The growing complexity of deep neural networks (DNNs) makes it increasingly difficult and important to explain the inner workings and…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Van Binh Truong , Truong Thanh Hung Nguyen , Vo Thanh Khang Nguyen , Quoc Khanh Nguyen , Quoc Hung Cao

VOT remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on visual cues, often struggle in such complex scenarios.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Mohamad Alansari , Sajid Javed , Iyyakutti Iyappan Ganapathi , Sara Alansari , Muzammal Naseer

3D visual grounding is a critical skill for household robots, enabling them to navigate, manipulate objects, and answer questions based on their environment. While existing approaches often rely on extensive labeled data or exhibit…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Jianing Yang , Xuweiyi Chen , Shengyi Qian , Nikhil Madaan , Madhavan Iyengar , David F. Fouhey , Joyce Chai

Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos. It essentially requires semantic comprehension and fine-grained video understanding. Existing methods introduce language…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Chen Liang , Yu Wu , Yawei Luo , Yi Yang

Humans learn by interacting with their environments and perceiving the outcomes of their actions. A landmark in artificial intelligence has been the development of deep reinforcement learning (dRL) algorithms capable of doing the same in…

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form. The process of separating underlying factors of variation…

Machine Learning · Computer Science 2024-06-28 Xin Wang , Hong Chen , Si'ao Tang , Zihao Wu , Wenwu Zhu

The challenge of dynamic view synthesis from dynamic monocular videos, i.e., synthesizing novel views for free viewpoints given a monocular video of a dynamic scene captured by a moving camera, mainly lies in accurately modeling the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Meng You , Junhui Hou

The ability to grasp ordinary and potentially never-seen objects is an important feature in both domestic and industrial robotics. For a system to accomplish this, it must autonomously identify grasping locations by using information from…

Robotics · Computer Science 2016-06-03 Ludovic Trottier , Philippe Giguère , Brahim Chaib-draa

Large Vision Language Models (VLMs), such as CLIP, have significantly contributed to various computer vision tasks, including object recognition and object detection. Their open vocabulary feature enhances their value. However, their…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Ali Rasekh , Sepehr Kazemi Ranjbar , Milad Heidari , Wolfgang Nejdl