Related papers: SJTU:Spatial judgments in multimodal models toward…

Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…

Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, augmented reality, and autonomous navigation. Unfortunately, existing benchmarks are inadequate…

Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…

Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure of the sensed scene (to know where it looks at) and…

In this work, we propose an end-to-end deep architecture that jointly learns to detect obstacles and estimate their depth for MAV flight applications. Most of the existing approaches either rely on Visual SLAM systems or on depth estimation…

General-purpose object-detection algorithms often dismiss the fine structure of detected objects. This can be traced back to how their proposed regions are evaluated. Our goal is to renegotiate the trade-off between the generality of these…

Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial stage fusion, leading to insufficient feature extraction and…

The state-of-the-art object detection and image classification methods can perform impressively on more than 9k and 10k classes, respectively. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This…

While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, visuospatial cognition - reasoning about spatial layouts, relations, and dynamics - remains a significant challenge. Existing models often lack the…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. We show that existing spatial VLMs lack basic camera motion…

Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, however, probe only single-image relations and thus fail to assess the multi-image spatial…

This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera. The proposed approach is based on a shared encoder-decoder architecture, which…

Multimodal Large Language Models (MLLMs) often struggle to accurately perceive fine-grained visual details, especially when targets are tiny or visually subtle. This challenge can be addressed through semantic-visual information fusion,…

We propose Perceptual Taxonomy, a structured process of scene understanding that first recognizes objects and their spatial configurations, then infers task-relevant properties such as material, affordance, function, and physical attributes…

Reliable Uncertainty Quantification (UQ) and failure prediction remain open challenges for Vision-Language Models (VLMs). We introduce ViLU, a new Vision-Language Uncertainty quantification framework that contextualizes uncertainty…

Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations. To…

Despite the recent success of deep learning in continuous sign language recognition (CSLR), deep models typically focus on the most discriminative features, ignoring other potentially non-trivial and informative contents. Such…

Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties…