457 citations · 552 across the 18 of their papers we have counts for
8 papers · 1 filter
UniCounting: Instance-Aware Proposal Consolidation for Image-Query-Free Multi-Category Counting
Jinshi Liu, Pan Liu, Lei He +2
Visual counting is commonly formulated as counting a single specified target, with a model receiving an image-specific exemplar, text query, or target category and returning a sing…
Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs
Jingyu Sun, Jiachen Tu, Yuyang Xue +8
Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself. Counterfactual i…
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Chaoyue Li, Boxue Yang, Shengyao Zhou +4
Language-guided dynamic scene understanding requires identifying one physical entity across time, metric 3D space, and multiple viewpoints, a setting not captured by current multim…
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
Rui Qian, Chuanhang Deng, Qiang Huang +6
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token $\texttt{…
UGround: Towards Unified Visual Grounding with Unrolled Transformers
Rui Qian, Xin Yin, Chuanhang Deng +4
We present UGround, a \textbf{U}nified visual \textbf{Ground}ing paradigm that dynamically selects intermediate layers across \textbf{U}nrolled transformers as ``mask as prompt,''…
Reasoning to Attend: Try to Understand How <SEG> Token Works
Rui Qian, Xin Yin, Dejing Dou
Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on tokens as a text prompt to jointly optimize the vision-language model (e.g., LL…
3D Object Detection for Autonomous Driving: A Survey
Rui Qian, Xin Lai, Xirong Li
Autonomous driving is regarded as one of the most promising remedies to shield human beings from severe crashes. To this end, 3D object detection serves as the core basis of percep…
BADet: Boundary-Aware 3D Object Detection from Point Clouds
Rui Qian, Xin Lai, Xirong Li
Currently, existing state-of-the-art 3D object detectors are in two-stage paradigm. These methods typically comprise two steps: 1) Utilize a region proposal network to propose a ha…