2 citations · 3 across the 19 of their papers we have counts for
20 papers
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
Zihan Wang, Hao Wang, Boyuan Jiang +8
Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time. We observe that, even afte…
MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models
Sihan Chen, Jiale Li, Jianghang Lin +1
Video Large Language Models (VideoLLMs) have shown strong progress in video understanding, yet they still suffer from hallucinations that are inconsistent with visual evidence. Exi…
Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Images
Yu Lin, Jianghang Lin, Kai Ye +2
Reducing the annotation cost of oriented object detection in remote sensing remains a major challenge. Recently, sparse annotation has gained attention for effectively reducing ann…
Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs
Jianghang Lin, Haihua Yang, Deli Yu +6
Multimodal Large Language Models (MLLMs) have shown transformative potential in medical applications, yet their performance is hindered by conventional data curation strategies tha…
HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
Yansong Guo, Chaoyang Zhu, Jiayi Ji +2
Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computat…
SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
Pengfei Yue, Xingran Zhao, Juntao Chen +6
Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on…
Referring Industrial Anomaly Segmentation
Pengfei Yue, Xiaokang Jiang, Yilin Lu +3
Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manu…
Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
Kai Ye, Xiaotong You, Jianghang Lin +3
Reasoning Segmentation requires models to interpret complex, context-dependent linguistic queries to achieve pixel-level localization. Current dominant approaches rely heavily on S…
Understanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions
Kai Ye, Bowen Liu, Jianghang Lin +3
Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on ge…
Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
Yilin Lu, Jianghang Lin, Linhuang Xie +5
Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples significantly limits the effectiveness of existing methods in tasks such as l…
What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
Jianghang Lin, Yue Hu, Jiangtao Shen +4
Open vocabulary image segmentation tackles the challenge of recognizing dynamically adjustable, predefined novel categories at inference time by leveraging vision-language alignmen…
Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
Jianghang Lin, Yilin Lu, Yunhang Shen +4
Semi-Supervised Instance Segmentation (SSIS) involves classifying and grouping image pixels into distinct object instances using limited labeled data. This learning paradigm usuall…
STeacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection
Yu Lin, Jianghang Lin, Kai Ye +5
Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotati…
AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis
Zhangyu Lai, Yilin Lu, Xinyang Li +5
While existing anomaly synthesis methods have made remarkable progress, achieving both realism and diversity in synthesis remains a major obstacle. To address this, we propose Anom…
Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation
Hongwei Niu, Linhuang Xie, Jianghang Lin +1
Domain Generalized Semantic Segmentation (DGSS) seeks to utilize source domain data exclusively to enhance the generalization of semantic segmentation across unknown target domains…
EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation
Hongwei Niu, Jie Hu, Jianghang Lin +2
Open-vocabulary panoptic segmentation aims to segment and classify everything in diverse scenes across an unbounded vocabulary. Existing methods typically employ two-stage or singl…
HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection
Liujuan Cao, Jianghang Lin, Zebo Hong +4
Most WSOD methods rely on traditional object proposals to generate candidate regions and are confronted with unstable training, which easily gets stuck in a poor local optimum. In…
Depth-Guided Semi-Supervised Instance Segmentation
Xin Chen, Jie Hu, Xiawu Zheng +3
Semi-Supervised Instance Segmentation (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled i…
GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane
Yansong Qu, Shaohui Dai, Xinyang Li +4
3D open-vocabulary scene understanding, crucial for advancing augmented reality and robotic applications, involves interpreting and locating specific regions within a 3D space as d…
Weakly Supervised Open-Vocabulary Object Detection
Jianghang Lin, Yunhang Shen, Bingquan Wang +3
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories withi…