366 citations · 1.6k across the 47 of their papers we have counts for
48 papers · 1 filter
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Yanbei Chen, Massimiliano Mancini, Xiatian Zhu +1
State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model'…
Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding
Xian Shi, Xun Xu, Wanyue Zhang +3
Semantic understanding of 3D point cloud relies on learning models with massively annotated data, which, in many cases, are expensive or difficult to collect. This has led to an em…
SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition
Victor Escorcia, Ricardo Guerrero, Xiatian Zhu +1
Learning an egocentric action recognition model from video data is challenging due to distractors (e.g., irrelevant objects) in the background. Further integrating object informati…
Knowledge Distillation Meets Open-Set Semi-Supervised Learning
Jing Yang, Xiatian Zhu, Adrian Bulat +2
Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is…
Unsupervised Noisy Tracklet Person Re-identification
Minxian Li, Xiatian Zhu, Shaogang Gong
Existing person re-identification (re-id) methods mostly rely on supervised model learning from a large set of person identity labelled training data per domain. This limits their…
Few-shot Action Recognition with Prototype-centered Attentive Learning
Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua +3
Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode…
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Sixiao Zheng, Jiachen Lu, Hengshuang Zhao +8
Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution a…
Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
Hui Tang, Xiatian Zhu, Ke Chen +2
Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose dist…
Boundary-sensitive Pre-training for Temporal Localization in Videos
Mengmeng Xu, Juan-Manuel Perez-Rua, Victor Escorcia +5
Many video analysis tasks require temporal localization thus detection of content changes. However, most existing models developed for these tasks are pre-trained on general video…
Egocentric Action Recognition by Video Attention and Temporal Context
Juan-Manuel Perez-Rua, Antoine Toisoul, Brais Martinez +4
We present the submission of Samsung AI Centre Cambridge to the CVPR2020 EPIC-Kitchens Action Recognition Challenge. In this challenge, action recognition is posed as the problem o…
Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
Juan-Manuel Perez-Rua, Brais Martinez, Xiatian Zhu +3
Attentive video modeling is essential for action recognition in unconstrained videos due to their rich yet redundant information over space and time. However, introducing attention…
Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
Hanbin Dai, Liangbo Zhou, Feng Zhang +4
In this paper, we focus on the coordinate representation in human pose estimation. While being the standard choice, heatmap based representation has not been systematically investi…
Incremental Few-Shot Object Detection
Juan-Manuel Perez-Rua, Xiatian Zhu, Timothy Hospedales +1
Most existing object detection methods rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements subst…
Intra-Camera Supervised Person Re-Identification
Xiangping Zhu, Xiatian Zhu, Minxian Li +3
Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data. This requires a tedious data collection and annotation…
Characteristic Regularisation for Super-Resolving Face Images
Zhiyi Cheng, Xiatian Zhu, Shaogang Gong
Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery. Such SR models, although strong at handling art…
Distribution-Aware Coordinate Representation for Human Pose Estimation
Feng Zhang, Xiatian Zhu, Hanbin Dai +2
While being the de facto standard coordinate representation in human pose estimation, heatmap is never systematically investigated in the literature, to our best knowledge. This wo…
Intra-Camera Supervised Person Re-Identification: A New Benchmark
Xiangping Zhu, Xiatian Zhu, Minxian Li +2
Existing person re-identification (re-id) methods rely mostly on a large set of inter-camera identity labelled training data, requiring a tedious data collection and annotation pro…
Universal Person Re-Identification
Xu Lan, Xiatian Zhu, Shaogang Gong
Most state-of-the-art person re-identification (re-id) methods depend on supervised model learning with a large set of cross-view identity labelled training data. Even worse, such…
Unsupervised Deep Learning by Neighbourhood Discovery
Jiabo Huang, Qi Dong, Shaogang Gong +1
Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training…
Unsupervised Tracklet Person Re-Identification
Minxian Li, Xiatian Zhu, Shaogang Gong
Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability…
Self-Referenced Deep Learning
Xu Lan, Xiatian Zhu, Shaogang Gong
Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running r…
Low-Resolution Face Recognition
Zhiyi Cheng, Xiatian Zhu, Shaogang Gong
Whilst recent face-recognition (FR) techniques have made significant progress on recognising constrained high-resolution web images, the same cannot be said on natively unconstrain…
Single-Label Multi-Class Image Classification by Deep Logistic Regression
Qi Dong, Xiatian Zhu, Shaogang Gong
The objective learning formulation is essential for the success of convolutional neural networks. In this work, we analyse thoroughly the standard learning objective functions for…
Fast Human Pose Estimation
Feng Zhang, Xiatian Zhu, Mao Ye
Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads…