Related papers: Geometry-Guided Camera Motion Understanding in Vid…
Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while the best text output achieves only 20.0…
Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that…
Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods…
Video Question Answering (VQA) requires models to reason over spatial, temporal, and causal cues in videos. Recent vision language models (VLMs) achieve strong results but often rely on shallow correlations, leading to weak temporal…
Geometric understanding - including depth and height perception - is fundamental to intelligence and crucial for navigating our environment. Despite the impressive capabilities of large Vision Language Models (VLMs), it remains unclear how…
Vision-language models (VLMs) classify the query video by calculating a similarity score between the visual features and text-based class label representations. Recently, large language models (LLMs) have been used to enrich the text-based…
Video quality assessment (VQA) is an important processing task, aiming at predicting the quality of videos in a manner highly consistent with human judgments of perceived quality. Traditional VQA models based on natural image and/or video…
Large video language models (LVLMs) have made notable progress in video understanding, spurring the development of corresponding evaluation benchmarks. However, existing benchmarks generally assess overall performance across entire video…
Recent advances in Image Quality Assessment (IQA) have leveraged Multi-modal Large Language Models (MLLMs) to generate descriptive explanations. However, despite their strong visual perception modules, these models often fail to reliably…
Sign language videos are an important medium for spreading and learning sign language. However, most existing human image synthesis methods produce sign language images with details that are distorted, blurred, or structurally incorrect.…
Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not…
Most current video MLLMs rely on uniform frame sampling and image-level encoders, resulting in inefficient data processing and limited motion awareness. To address these challenges, we introduce EMA, an Efficient Motion-Aware video MLLM…
We present Video-LLaMA a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen…
Low-Light Enhancement (LLE) is aimed at improving the quality of photos/videos captured under low-light conditions. It is worth noting that most existing LLE methods do not take advantage of geometric modeling. We believe that incorporating…
Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the…
Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and…
Video-based numerical reasoning provides a premier arena for testing whether Vision-Language Models (VLMs) truly "understand" real-world dynamics, as accurate numerical deduction necessitates a profound grasp of temporal events, object…
Vision-language foundation models (VLMs) have shown impressive performance in guiding image generation through text, with emerging applications in medical imaging. In this work, we are the first to investigate the question: 'Can fine-tuned…
Do we still need to represent objects explicitly in multimodal large language models (MLLMs)? To one extreme, pre-trained encoders convert images into visual tokens, with which objects and spatiotemporal relationships may be implicitly…
Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains…