11 papers
Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference
Tong Jin, Yunpeng Liu, Shuyu Hu +4
Recent visual place recognition (VPR) methods based on vision transformers, particularly foundation models, have achieved remarkable recognition performance. However, these models…
Selectivity Drives Efficiency: Dataset Pruning for Visual Place Recognition
Tong Jin, Yunpeng Liu, Shuyu Hu +3
Recent visual place recognition (VPR) studies have increasingly relied on large-scale datasets to train more robust and discriminative models. Although this trend significantly imp…
Online Reasoning Video Object Segmentation
Jinyuan Liu, Yang Wang, Zeyu Zhao +3
Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries that may involve implicit and temporally grounded references. However, existi…
Data-Efficient Surgical Phase Segmentation in Small-Incision Cataract Surgery: A Controlled Study of Vision Foundation Models
Lincoln Spencer, Song Wang, Chen Chen
Surgical phase segmentation is central to computer-assisted surgery, yet robust models remain difficult to develop when labeled surgical videos are scarce. We study data-efficient…
AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments
Xuzhi Wang, Xinran Wu, Song Wang +2
Indoor monocular semantic scene completion (MSSC) is notably more challenging than its outdoor counterpart due to complex spatial layouts and severe occlusions. While transformers…
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Sicheng Feng, Kaiwen Tuo, Song Wang +3
Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even adva…
3D and 4D World Modeling: A Survey
Lingdong Kong, Yu Yang, Jianbiao Mei +20
World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphas…
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
Xiang Xu, Lingdong Kong, Song Wang +2
LiDAR representation learning aims to extract rich structural and semantic information from large-scale, readily available datasets, reducing reliance on costly human annotations.…
SAM4D: Segment Anything in Camera and LiDAR Streams
Jianyun Xu, Song Wang, Ziqian Ni +4
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) i…
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
Song Wang, Gongfan Fang, Lingdong Kong +6
Existing reasoning segmentation approaches typically fine-tune multimodal large language models (MLLMs) using image-text pairs and corresponding mask labels. However, they exhibit…
ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps
Sicheng Feng, Song Wang, Shuyi Ouyang +5
Multimodal large language models (MLLMs) have demonstrated significant progress in semantic scene understanding and text-image alignment, with reasoning variants enhancing performa…