MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentationby Yuanbing Zhu, Bingke…
PAM: A Propagation-Based Model for Segmenting Any 3D Objects across Multi-Modal Medical Imagesby Zifan Chen,…
Focused Large Language Models are Stable Many-Shot Learnersby Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin…
Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videosby Jiajun Fei,…
Pixel-Aligned Multi-View Generation with Depth Guided Decoderby Zhenggang Tang, Peiye Zhuang, Chaoyang Wang, Aliaksandr Siarohin,…
Contrastive Learning Subspace for Text Clusteringby Qian Yong, Chen Chen, Xiabing ZhouFirst submitted to arxiv…
MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinementby Xu He,…
Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approachby Jiwei Guan, Tianyu…
Spatio-Temporal Road Traffic Prediction using Real-time Regional Knowledgeby Sumin Han, Jisun An, Dongman LeeFirst submitted…
Multiple Areal Feature Aware Transportation Demand Predictionby Sumin Han, Jisun An, Youngjun Park, Suji Kim,…