Related papers: Motion-o: Trajectory-Grounded Video Reasoning
Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and…
Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and…
The trajectory patterns of a moving object in a spatio-temporal domain offers varied information in terms of the management of the data generated from the movement. A trajectory data warehouse is a data repository for the data and…
Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning, which gains increasing attention. Nevertheless, the current MCoT benchmark still faces some…
The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning…
Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language models improve geometric perception and long-range context…
Vision-Language Models (VLMs) demonstrate strong general-purpose reasoning but remain limited in physics-grounded anomaly detection, where causal understanding of dynamics is essential. Existing VLMs, trained predominantly on…
Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large…
Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large…
Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent…
Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a novel approach to address this gap by translating physical-world…
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…
There has been growing sentiment recently that modern large multimodal models (LMMs) have addressed most of the key challenges related to short video comprehension. As a result, both academia and industry are gradually shifting their…
Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evidence from both modalities. A central limitation is that…
We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames. An essential property of camouflaged objects…
Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual…
The capability of making explainable inferences regarding physical processes has long been desired. One fundamental physical process is object motion. Inferring what causes the motion of a group of objects can even be a challenging task for…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning…
This work addresses continuous space-time video super-resolution (C-STVSR) that aims to up-scale an input video both spatially and temporally by any scaling factors. One key challenge of C-STVSR is to propagate information temporally among…
Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in…