相关论文: SteerSeg: Attention Steering for Reasoning Video S…
Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…
Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and…
Recently, multi-modal large language models have made significant progress. However, visual information lacking of guidance from the user's intention may lead to redundant computation and involve unnecessary visual noise, especially in…
Pretrained vision-language models (VLMs), \eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images…
Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…
Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…
Large-scale vision-language models (VLMs), trained on extensive datasets of image-text pairs, exhibit strong multimodal understanding capabilities by implicitly learning associations between textual descriptions and image regions. This…
While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…
Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video…
Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…
Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive…
When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…
Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when needed, actively seeking additional viewpoints during…
Reasoning segmentation is a challenging vision-language task that aims to output the segmentation mask with respect to a complex, implicit, and even non-visual query text. Previous works incorporated multimodal Large Language Models (MLLMs)…
In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as…
Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…
Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation steering. However,…
Temporal Action Detection and Moment Retrieval constitute two pivotal tasks in video understanding, focusing on precisely localizing temporal segments corresponding to specific actions or events. Recent advancements introduced Moment…
Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot…
Current high-performance semantic segmentation models are purely data-driven sub-symbolic approaches and blind to the structured nature of the visual world. This is in stark contrast to human cognition which abstracts visual perceptions at…