Related papers: LocateAnything: Fast and High-Quality Vision-Langu…
In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \textbf{MMTrack}, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with…
Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…
Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…
Earth vision has achieved milestones in geospatial object recognition but lacks exploration in object-relational reasoning, limiting comprehensive scene understanding. To address this, a progressive Earth vision-language understanding and…
Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on…
Visual Grounding (VG) aims to utilize given natural language queries to locate specific target objects within images. While current transformer-based approaches demonstrate strong localization performance in standard scene (i.e, scenarios…
We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification…
Visual grounding aims to identify objects or regions in a scene based on natural language descriptions, essential for spatially aware perception in autonomous driving. However, existing visual grounding tasks typically depend on bounding…
Spatio-Temporal Video Grounding requires jointly localizing target objects across both temporal and spatial dimensions based on natural language queries, posing fundamental challenges for existing Multimodal Large Language Models (MLLMs).…
Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…
Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad implications for robotics, augmented reality,…
The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital integrity. Vision-language models (VLMs) can provide natural language explanations, but standard…
Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, existing pipelines typically decouple motion quantization from…
Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring cross-viewpoint understanding and spatial reasoning. We…
Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate representations as constraints to reduce the uncertainties and improve the consistencies between the 2D…
Despite significant advances in vision-language understanding, implementing image segmentation within multimodal architectures remains a fundamental challenge in modern artificial intelligence systems. Existing vision-language models, which…
Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…
Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…
Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary…
Regular object detection methods output rectangle bounding boxes, which are unable to accurately describe the actual object shapes. Instance segmentation methods output pixel-level labels, which are computationally expensive for real-time…