434 citations · 1.3k across the 60 of their papers we have counts for
55 papers · 1 filter
UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning
Meiqi Sun, Zhonghan Zhao, Wenhao Chai +5
Animal visual perception is an important technique for automatically monitoring animal health, understanding animal behaviors, and assisting animal-related research. However, it is…
A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision
Zhonghan Zhao, Wenhao Chai, Shengyu Hao +6
Deep learning has the potential to revolutionize sports performance, with applications ranging from perception and comprehension to decision. This paper presents a comprehensive su…
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Enxin Song, Wenhao Chai, Guanhong Wang +10
Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet…
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation
Zhongyu Jiang, Zhuoran Zhou, Lei Li +3
Learning-based methods have dominated the 3D human pose estimation (HPE) tasks with significantly better performance in most benchmarks than traditional optimization-based methods.…
MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling
Zhenyu Zhang, Wenhao Chai, Zhongyu Jiang +4
Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years. Yet, prior to this, no such work has attempted to unify 2D and 3D pose represen…
Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports
Hsiang-Wei Huang, Cheng-Yen Yang, Jiacheng Sun +5
Deep learning-based object detectors have driven notable progress in multi-object tracking algorithms. Yet, current tracking methods mainly focus on simple, regular motion patterns…
Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching
Shuting Xia, Tingyu Fan, Yiling Xu +2
3D dynamic point cloud (DPC) compression relies on mining its temporal context, which faces significant challenges due to DPC's sparsity and non-uniform structure. Existing methods…
Multi-Object Tracking by Iteratively Associating Detections with Uniform Appearance for Trawl-Based Fishing Bycatch Monitoring
Cheng-Yen Yang, Alan Yu Shyang Tan, Melanie J. Underwood +6
The aim of in-trawl catch monitoring for use in fishing operations is to detect, track and classify fish targets in real-time from video footage. Information gathered could be used…
Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment
Hsiang-Wei Huang, Cheng-Yen Yang, Zhongyu Jiang +8
Multi-camera multiple people tracking has become an increasingly important area of research due to the growing demand for accurate and efficient indoor people tracking systems, par…
Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation
Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang +1
When applying a pre-trained 2D-to-3D human pose lifting model to a target unseen dataset, large performance degradation is commonly encountered due to domain shift issues. We obser…
DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes
Shenghao Hao, Peiyuan Liu, Yibing Zhan +5
Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased at…
CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations
Cheng-Yen Yang, Jiajia Luo, Lu Xia +5
To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augment…
Multi-target multi-camera vehicle tracking using transformer-based camera link model and spatial-temporal information
Hsiang-Wei Huang, Cheng-Yen Yang, Jenq-Neng Hwang
Multi-target multi-camera tracking (MTMCT) of vehicles, i.e. tracking vehicles across multiple cameras, is a crucial application for the development of smart city and intelligent t…
1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
Benjamin Kiefer, Matej Kristan, Janez Perš +70
The 1 Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and…
HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar
Shih-Po Lee, Niraj Prakash Kini, Wen-Hsiao Peng +2
This paper introduces a novel human pose estimation benchmark, Human Pose with Millimeter Wave Radar (HuPR), that includes synchronized vision and radio signal components. This dat…
Image-Text Retrieval with Binary and Continuous Label Supervision
Zheng Li, Caili Guo, Zerun Feng +3
Most image-text retrieval work adopts binary labels indicating whether a pair of image and text matches or not. Such a binary indicator covers only a limited subset of image-text s…
Observation Centric and Central Distance Recovery on Sports Player Tracking
Hsiang-Wei Huang, Cheng-Yen Yang, Jenq-Neng Hwang +3
Multi-Object Tracking over humans has improved rapidly with the development of object detection and re-identification. However, multi-actor tracking over humans with similar appear…
Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
Zheng Li, Caili Guo, Xin Wang +3
There are two popular loss functions used for vision-language retrieval, i.e., triplet loss and contrastive learning loss, both of them essentially minimize the difference between…
GaitTAKE: Gait Recognition by Temporal Attention and Keypoint-guided Embedding
Hung-Min Hsu, Yizhou Wang, Cheng-Yen Yang +3
Gait recognition, which refers to the recognition or identification of a person based on their body shape and walking styles, derived from video data captured from a distance, is w…
GLIPv2: Unifying Localization and Vision-Language Understanding
Haotian Zhang, Pengchuan Zhang, Xiaowei Hu +7
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tas…
Unsupervised Domain Adaptation Learning for Hierarchical Infant Pose Recognition with Synthetic Data
Cheng-Yen Yang, Zhongyu Jiang, Shih-Yu Gu +2
The Alberta Infant Motor Scale (AIMS) is a well-known assessment scheme that evaluates the gross motor development of infants by recording the number of specific poses achieved. Wi…
Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
Gaoang Wang, Mingli Song, Jenq-Neng Hwang
Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the…
TR-MOT: Multi-Object Tracking by Reference
Mingfei Chen, Yue Liao, Si Liu +2
Multi-object Tracking (MOT) generally can be split into two sub-tasks, i.e., detection and association. Many previous methods follow the tracking by detection paradigm, which first…
The Overlooked Classifier in Human-Object Interaction Recognition
Ying Jin, Yinpeng Chen, Lijuan Wang +5
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows…