31 citations · 97 across the 25 of their papers we have counts for
24 papers
DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs
Jiawen Zhu, Huayi Tang, Zhi-Qi Cheng +5
Existing nighttime unmanned aerial vehicle (UAV) trackers follow an "Enhance-then-Track" architecture - first using a light enhancer to brighten the nighttime video, then employing…
Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation
Hanbing Liu, Wangmeng Xiang, Jun-Yan He +4
Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture. With the success of transformers, we introduce the Refined…
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
Junwen He, Yifan Wang, Lijun Wang +6
Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pur…
PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation
Hanbing Liu, Jun-Yan He, Zhi-Qi Cheng +8
Existing 3D human pose estimators face challenges in adapting to new datasets due to the lack of 2D-3D pose pairs in training sets. To overcome this issue, we propose \textit{Multi…
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
Qihang Yu, Ju He, Xueqing Deng +2
Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage mul…
Tracking Anything in High Quality
Jiawen Zhu, Zhenyu Chen, Zeqi Hao +9
Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject…
Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation
Ju He, Jieneng Chen, Ming-Xian Lin +2
In this work, we present a robust approach for joint part and object segmentation. Specifically, we reformulate object and part segmentation as an optimization problem and build a…
KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration
Xu Bao, Zhi-Qi Cheng, Jun-Yan He +8
Accurate facial landmark detection is critical for facial analysis tasks, yet prevailing heatmap and coordinate regression methods grapple with prohibitive computational costs and…
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He +3
Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human j…
DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving
Jun-Yan He, Zhi-Qi Cheng, Chenyang Li +5
Real-time perception, or streaming perception, is a crucial aspect of autonomous driving that has yet to be thoroughly explored in existing research. To address this gap, we presen…
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
Hanyuan Chen, Jun-Yan He, Wangmeng Xiang +6
Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insuffici…
Differentially Private Heatmaps
Badih Ghazi, Junfeng He, Kai Kohlhoff +4
We consider the task of producing heatmaps from users' aggregated data while protecting their privacy. We give a differentially private (DP) algorithm for this task and demonstrate…
ProContEXT: Exploring Progressive Context Transformer for Tracking
Jin-Peng Lan, Zhi-Qi Cheng, Jun-Yan He +6
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as i…
PartImageNet: A Large, High-Quality Dataset of Parts
Ju He, Shuo Yang, Shaokang Yang +7
It is natural to represent objects in terms of their parts. This has the potential to improve the performance of algorithms for object recognition and segmentation but can also hel…
TransMix: Attend to Mix for Vision Transformers
Jie-Neng Chen, Shuyang Sun, Ju He +3
Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, p…
OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images
Bingchen Zhao, Shaozuo Yu, Wufei Ma +6
Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on syntheti…
Learning from Temporal Gradient for Semi-supervised Action Recognition
Junfei Xiao, Longlong Jing, Lin Zhang +5
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are m…
Deep Saliency Prior for Reducing Visual Distraction
Kfir Aberman, Junfeng He, Yossi Gandelsman +5
Using only a model that was trained to predict where people look at images, and no additional training data, we can produce a range of powerful editing effects for reducing distrac…
Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
Ju He, Adam Kortylewski, Shaokang Yang +4
Semi-Supervised Learning (SSL) has shown its strong ability in utilizing unlabeled data when labeled data is scarce. However, most SSL algorithms work under the assumption that the…
TransFG: A Transformer Architecture for Fine-grained Recognition
Ju He, Jie-Neng Chen, Shuai Liu +4
Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most…
Semi-synthesis: A fast way to produce effective datasets for stereo matching
Ju He, Enyu Zhou, Liusheng Sun +3
Stereo matching is an important problem in computer vision which has drawn tremendous research attention for decades. Recent years, data-driven methods with convolutional neural ne…
CORL: Compositional Representation Learning for Few-Shot Classification
Ju He, Adam Kortylewski, Alan Yuille
Few-shot image classification consists of two consecutive learning processes: 1) In the meta-learning stage, the model acquires a knowledge base from a set of training classes. 2)…
Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
Adam Kortylewski, Ju He, Qing Liu +1
Recent findings show that deep convolutional neural networks (DCNNs) do not generalize well under partial occlusion. Inspired by the success of compositional models at classifying…
Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
Wei Hu, Gusi Te, Ju He +2
Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks. Previous model-based and deep learning approaches achieve satisfactory performa…