353 citations · 701 across the 20 of their papers we have counts for
20 papers
Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
Chi Zhang, Haibo Qiu, Qiming Zhang +3
We present Seirênes, a self-play RL framework that transforms contextual interference from a failure mode of LLM reasoning into an internal training signal for co-evolving more res…
When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability
Wenjie Xuan, Yufei Xu, Shanshan Zhao +4
ControlNet excels at creating content that closely matches precise contours in user-provided masks. However, when these masks contain noise, as a frequent occurrence with non-exper…
APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond
Yuxiang Yang, Yingqi Deng, Yufei Xu +1
Animal Pose Estimation and Tracking (APT) is a critical task in detecting and monitoring the keypoints of animals across a series of video frames, which is essential for understand…
HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting
Wenquan Lu, Yufei Xu, Jing Zhang +2
Diffusion models have achieved remarkable success in generating realistic images but suffer from generating accurate human hands, such as incorrect finger counts or irregular shape…
Empowering Agrifood System with Artificial Intelligence: A Survey of the Progress, Challenges and Opportunities
Tao Chen, Liang Lv, Di Wang +12
With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shorta…
Vision Transformer with Quadrangle Attention
Qiming Zhang, Jing Zhang, Yufei Xu +1
Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the d…
ViTPose++: Vision Transformer for Generic Body Pose Estimation
Yufei Xu, Jing Zhang, Qiming Zhang +1
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalabilit…
Rethinking Hierarchies in Pre-trained Plain Vision Transformer
Yufei Xu, Jing Zhang, Qiming Zhang +1
Self-supervised pre-training vision transformer (ViT) via masked image modeling (MIM) has been proven very effective. However, customized algorithms should be carefully designed fo…
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
Di Wang, Qiming Zhang, Yufei Xu +4
Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalabili…
Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
Zhe Chen, Jing Zhang, Yufei Xu +1
Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and…
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
Xu Zhang, Wen Wang, Zhe Chen +3
Animal pose estimation is challenging for existing image-based methods because of limited training data and large intra- and inter-species variances. Motivated by the progress of v…
APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking
Yuxiang Yang, Junjie Yang, Yufei Xu +3
Animal pose estimation and tracking (APT) is a fundamental task for detecting and tracking animal keypoints from a sequence of video frames. Previous animal-related datasets focus…
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
Yufei Xu, Jing Zhang, Qiming Zhang +1
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual recognition tasks. However, little effort ha…
VSA: Learning Varied-Size Window Attention in Vision Transformers
Qiming Zhang, Yufei Xu, Jing Zhang +1
Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint. However, current models adopt a h…
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Qiming Zhang, Yufei Xu, Jing Zhang +1
Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism.…
RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?
Yufei Xu, Qiming Zhang, Jing Zhang +1
Self-supervised methods (SSL) have achieved significant success via maximizing the mutual information between two augmented views, where cropping is a popular augmentation techniqu…
Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization
Yufei Xu, Jing Zhang, Dacheng Tao
Warping-based video stabilizers smooth camera trajectory by constraining each pixel's displacement and warp stabilized frames from unstable ones accordingly. However, since the vie…
AP-10K: A Benchmark for Animal Pose Estimation in the Wild
Hang Yu, Yufei Xu, Jing Zhang +3
Accurate animal pose estimation is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation.…
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
Yufei Xu, Qiming Zhang, Jing Zhang +1
Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Neve…
DUT: Learning Video Stabilization by Simply Watching Unstable Videos
Yufei Xu, Jing Zhang, Stephen J. Maybank +1
Previous deep learning-based video stabilizers require a large scale of paired unstable and stable videos for training, which are difficult to collect. Traditional trajectory-based…