8 citations · 26 across the 18 of their papers we have counts for
21 papers
Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
Yuqi Huang, Hui Li, Yifei Cao +9
Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challenging. Human demonstrations conv…
Unified Multimodal Visual Tracking with Dual Mixture-of-Experts
Lingyi Hong, Jinglun Li, Xinyu Zhou +6
Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing methods often train separate mo…
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
AGI Team, Yuxuan Cai, Lu Chen +62
The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incent…
Dynamic Semantic-Aware Correlation Modeling for UAV Tracking
Xinyu Zhou, Tongxin Pan, Lingyi Hong +5
UAV tracking can be widely applied in scenarios such as disaster rescue, environmental monitoring, and logistics transportation. However, existing UAV tracking methods predominantl…
Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
Kaixun Jiang, Zhaoyu Chen, Haijing Guo +6
Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted ad…
DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
Xinyu Zhou, Jinglun Li, Lingyi Hong +4
Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods hea…
VideoSAM: Open-World Video Segmentation
Pinxue Guo, Zixu Zhao, Jianxiong Gao +5
Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video f…
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
Pinxue Guo, Wanyun Li, Hao Huang +7
Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where tr…
General Compression Framework for Efficient Transformer Object Tracking
Lingyi Hong, Jinglun Li, Xinyu Zhou +10
Previous works have attempted to improve tracking efficiency through lightweight architecture design or knowledge distillation from teacher models to compact student trackers. Howe…
Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection
Jinglun Li, Xinyu Zhou, Pinxue Guo +4
Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling sche…
TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning
Jinglun Li, Xinyu Zhou, Kaixun Jiang +5
Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing meth…
Improving Adversarial Transferability with Neighbourhood Gradient Information
Haijing Guo, Jiafeng Wang, Zhaoyu Chen +5
Deep neural networks (DNNs) are known to be susceptible to adversarial examples, leading to significant performance degradation. In black-box attack scenarios, a considerable attac…
LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation
Lingyi Hong, Zhongying Liu, Wenchao Chen +9
Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchm…
OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
Lingyi Hong, Shilin Yan, Renrui Zhang +8
Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be d…
OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework
Wanyun Li, Pinxue Guo, Xinyu Zhou +5
Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanc…
ClickVOS: Click Video Object Segmentation
Pinxue Guo, Lingyi Hong, Xinyu Zhou +7
Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame d…
Reading Relevant Feature from Global Representation Memory for Visual Object Tracking
Xinyu Zhou, Pinxue Guo, Lingyi Hong +4
Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object t…
OpenVIS: Open-vocabulary Video Instance Segmentation
Pinxue Guo, Tony Huang, Peiyang He +4
Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect, segment, and track arbitrary object categories in a video, without being constrained to categories…
Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation
Yuzheng Wang, Zhaoyu Chen, Dingkang Yang +4
Adversarial Robustness Distillation (ARD) is a promising task to solve the issue of limited adversarial robustness of small capacity models while optimizing the expensive computati…
Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang +5
Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial…
LVOS: A Benchmark for Long-term Video Object Segmentation
Lingyi Hong, Wenchao Chen, Zhongying Liu +4
Existing video object segmentation (VOS) benchmarks focus on short-term videos which just last about 3-5 seconds and where objects are visible most of the time. These videos are po…