Search Results for author: Xiatian Zhu

Found 76 papers, 34 papers with code

Visual Representation Learning with Transformer: A Sequence-to-Sequence Perspective

1 code implementation19 Jul 2022 Li Zhang, Sixiao Zheng, Jiachen Lu, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng

Extensive experiments show that our method achieves appealing performance on a variety of visual recognition tasks (e. g., image classification, object detection and instance segmentation and semantic segmentation).

Image Classification Instance Segmentation +4

FashionViL: Fashion-Focused Vision-and-Language Representation Learning

1 code implementation17 Jul 2022 Xiao Han, Licheng Yu, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang

We thus propose a Multi-View Contrastive Learning task for pulling closer the visual representation of one image to the compositional multimodal representation of another image+text.

Contrastive Learning Image Retrieval +1

Zero-Shot Temporal Action Detection via Vision-Language Prompting

1 code implementation17 Jul 2022 Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

Such a novel design effectively eliminates the dependence between localization and classification by breaking the route for error propagation in-between.

Action Detection Classification +3

Temporal Action Detection with Global Segmentation Mask Learning

2 code implementations14 Jul 2022 Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

Existing temporal action detection (TAD) methods rely on generating an overwhelmingly large number of proposals per video.

Action Detection Representation Learning +1

Semi-Supervised Temporal Action Detection with Proposal-Free Masking

1 code implementation14 Jul 2022 Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

Such a novel design effectively eliminates the dependence between localization and classification by cutting off the route for error propagation in-between.

Action Detection Classification +1

Softmax-free Linear Transformers

1 code implementation5 Jul 2022 Jiachen Lu, Li Zhang, Junge Zhang, Xiatian Zhu, Hang Xu, Jianfeng Feng

Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

Natural Language Processing

Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

1 code implementation5 Jul 2022 Hengyuan Ma, Li Zhang, Xiatian Zhu, Jianfeng Feng

However, a fundamental limitation is that their inference is very slow due to a need for many (e. g., 2000) iterations of sequential computations.

Image Generation

PolarFormer: Multi-camera 3D Object Detection with Polar Transformers

1 code implementation30 Jun 2022 Yanqin Jiang, Li Zhang, Zhenwei Miao, Xiatian Zhu, Jin Gao, Weiming Hu, Yu-Gang Jiang

3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world.

2D object detection 3D Object Detection +4

ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning for Action Recognition

no code implementations27 Jun 2022 Junting Pan, Ziyi Lin, Xiatian Zhu, Jing Shao, Hongsheng Li

However, existing attempts typically focus on downstream tasks from the same modality (e. g., image understanding) of the pre-trained model.

Ranked #6 on Action Classification on Kinetics-400 (using extra training data)

Action Classification Action Recognition +2

Multimodal Learning with Transformers: A Survey

no code implementations13 Jun 2022 Peng Xu, Xiatian Zhu, David A. Clifton

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks.

Learning Ego 3D Representation as Ray Tracing

1 code implementation8 Jun 2022 Jiachen Lu, Zheyuan Zhou, Xiatian Zhu, Hang Xu, Li Zhang

A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in order to ground downstream planner.

3D Object Detection Depth Estimation +3

Accelerating Score-based Generative Models for High-Resolution Image Synthesis

no code implementations8 Jun 2022 Hengyuan Ma, Li Zhang, Xiatian Zhu, Jingfeng Zhang, Jianfeng Feng

To ensure stability of convergence in sampling and generation quality, however, this sequential sampling process has to take a small step size and many sampling iterations (e. g., 2000).

Image Generation

Knowledge Distillation Meets Open-Set Semi-Supervised Learning

1 code implementation13 May 2022 Jing Yang, Xiatian Zhu, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

The key idea is that we leverage the teacher's classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions.

Face Recognition Knowledge Distillation

EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

2 code implementations6 May 2022 Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais Martinez

In this work, pushing further along this under-studied direction we introduce EdgeViTs, a new family of light-weight ViTs that, for the first time, enable attention-based vision models to compete with the best light-weight CNNs in the tradeoff between accuracy and on-device efficiency.

SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition

no code implementations10 Apr 2022 Victor Escorcia, Ricardo Guerrero, Xiatian Zhu, Brais Martinez

To overcome both limitations, we introduce Self-Supervised Learning Over Sets (SOS), an approach to pre-train a generic Objects In Contact (OIC) representation model from video object regions detected by an off-the-shelf hand-object contact detector.

Action Recognition Self-Supervised Learning

Unsupervised Long-Term Person Re-Identification with Clothes Change

no code implementations7 Feb 2022 Mingkun Li, Peng Xu, Xiatian Zhu, Jun Guo

We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment.

Unsupervised Person Re-Identification

Source-Free Object Detection by Learning To Overlook Domain Style

1 code implementation CVPR 2022 Shuaifeng Li, Mao Ye, Xiatian Zhu, Lihua Zhou, Lin Xiong

This approach suffers from both unsatisfactory accuracy of pseudo labels due to the presence of domain shift and limited use of target domain training data.

object-detection Object Detection

SOFT: Softmax-free Transformer with Linear Complexity

1 code implementation NeurIPS 2021 Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, Li Zhang

Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

Natural Language Processing

Few-Shot Temporal Action Localization with Query Adaptive Transformer

1 code implementation20 Oct 2021 Sauradip Nag, Xiatian Zhu, Tao Xiang

Further, a novel FS-TAL model is proposed which maximizes the knowledge transfer from training classes whilst enabling the model to be dynamically adapted to both the new class and each video of that class simultaneously.

Action Segmentation Few Shot Temporal Action Localization +4

Temporal Action Localization with Global Segmentation Mask Transformers

no code implementations29 Sep 2021 Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

In this paper, to address the above two challenges, a novel {\em Global Segmentation Mask Transformer} (GSMT) is proposed.

object-detection Object Detection +1

Single Person Pose Estimation: A Survey

no code implementations21 Sep 2021 Feng Zhang, Xiatian Zhu, Chen Wang

Human pose estimation in unconstrained images and videos is a fundamental computer vision task.

Data Augmentation Pose Estimation

Low-resolution Human Pose Estimation

no code implementations19 Sep 2021 Chen Wang, Feng Zhang, Xiatian Zhu, Shuzhi Sam Ge

Human pose estimation has achieved significant progress on images with high imaging resolution.

Pose Estimation

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer

1 code implementation ICCV 2021 Zhihe Lu, Sen He, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels).

Few-Shot Semantic Segmentation Meta-Learning +1

Global Aggregation then Local Distribution for Scene Parsing

1 code implementation28 Jul 2021 Xiangtai Li, Li Zhang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Xiatian Zhu, Tao Xiang

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation.

Scene Parsing Semantic Segmentation

DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change

1 code implementation31 May 2021 Peng Xu, Xiatian Zhu

Currently, one of the most significant limitations in this field is the lack of a large realistic benchmark.

Person Identification Person Re-Identification

Few-Shot Website Fingerprinting Attack

no code implementations25 Jan 2021 Mantun Chen, Yongjun Wang, Zhiquan Qin, Xiatian Zhu

To address this, we introduce a model-agnostic, efficient, and Harmonious Data Augmentation (HDA) method that can improve deep WF attacking methods significantly.

Data Augmentation Cryptography and Security 68M25 K.4.1

Few-shot Action Recognition with Prototype-centered Attentive Learning

1 code implementation20 Jan 2021 Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua, Li Zhang, Brais Martinez, Tao Xiang

Extensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (10+\%) on the most challenging fine-grained action recognition benchmark.

Contrastive Learning Few Shot Action Recognition +2

Unsupervised Noisy Tracklet Person Re-identification

no code implementations16 Jan 2021 Minxian Li, Xiatian Zhu, Shaogang Gong

Extensive comparative experiments demonstrate that the proposed STL model surpasses significantly the state-of-the-art unsupervised learning and one-shot learning re-id methods on three large tracklet person re-id benchmarks.

One-Shot Learning Person Re-Identification

Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering

2 code implementations8 Dec 2020 Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, C. L. Philip Chen

To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption.

Deep Clustering Image Classification +2

Egocentric Action Recognition by Video Attention and Temporal Context

no code implementations3 Jul 2020 Juan-Manuel Perez-Rua, Antoine Toisoul, Brais Martinez, Victor Escorcia, Li Zhang, Xiatian Zhu, Tao Xiang

In this challenge, action recognition is posed as the problem of simultaneously predicting a single `verb' and `noun' class label given an input trimmed video clip.

Action Recognition

Incremental Few-Shot Object Detection

no code implementations CVPR 2020 Juan-Manuel Perez-Rua, Xiatian Zhu, Timothy Hospedales, Tao Xiang

To this end we propose OpeN-ended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples.

Few-Shot Learning Few-Shot Object Detection +2

Intra-Camera Supervised Person Re-Identification

no code implementations12 Feb 2020 Xiangping Zhu, Xiatian Zhu, Minxian Li, Pietro Morerio, Vittorio Murino, Shaogang Gong

Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data.

Person Re-Identification

Characteristic Regularisation for Super-Resolving Face Images

no code implementations30 Dec 2019 Zhiyi Cheng, Xiatian Zhu, Shaogang Gong

Extensive evaluations demonstrate the performance superiority of our method over state-of-the-art SR and UDA models on both genuine and artificial LR facial imagery data.

Image Super-Resolution Unsupervised Domain Adaptation

Distribution-Aware Coordinate Representation for Human Pose Estimation

6 code implementations CVPR 2020 Feng Zhang, Xiatian Zhu, Hanbin Dai, Mao Ye, Ce Zhu

Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before.

Ranked #3 on Multi-Person Pose Estimation on COCO (using extra training data)

Keypoint Detection Multi-Person Pose Estimation

Neural Operator Search

no code implementations25 Sep 2019 Wei Li, Shaogang Gong, Xiatian Zhu

We address this limitation by additionally exploiting feature self-calibration operations, resulting in a heterogeneous search space.

Neural Architecture Search

Intra-Camera Supervised Person Re-Identification: A New Benchmark

no code implementations27 Aug 2019 Xiangping Zhu, Xiatian Zhu, Minxian Li, Vittorio Murino, Shaogang Gong

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 process therefore leading to poor scalability in practical re-id applications.

Multi-Label Learning Person Re-Identification

Universal Person Re-Identification

no code implementations22 Jul 2019 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.

Domain Generalization Person Re-Identification +1

Unsupervised Deep Learning by Neighbourhood Discovery

1 code implementation25 Apr 2019 Jiabo Huang, Qi Dong, Shaogang Gong, Xiatian Zhu

Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations.

Image Classification

Low-Resolution Face Recognition

no code implementations21 Nov 2018 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 unconstrained low-resolution images at large scales.

Face Recognition Super-Resolution

Self-Referenced Deep Learning

no code implementations19 Nov 2018 Xu Lan, Xiatian Zhu, Shaogang Gong

Whilst being able to create stronger target networks compared to the vanilla non-teacher based learning strategy, this scheme needs to train additionally a large teacher model with expensive computational cost.

Knowledge Distillation

Fast Human Pose Estimation

1 code implementation CVPR 2019 Feng Zhang, Xiatian Zhu, Mao Ye

In this work, we investigate the under-studied but practically critical pose model efficiency problem.

Pose Estimation

Vehicle Re-Identification in Context

no code implementations25 Sep 2018 Aytaç Kanacı, Xiatian Zhu, Shaogang Gong

Existing vehicle re-identification (re-id) evaluation benchmarks consider strongly artificial test scenarios by assuming the availability of high quality images and fine-grained appearance at an almost constant image scale, reminiscent to images required for Automatic Number Plate Recognition, e. g. VeRi-776.

Vehicle Re-Identification

Semi-Supervised Deep Learning with Memory

1 code implementation ECCV 2018 Yanbei Chen, Xiatian Zhu, Shaogang Gong

We consider the semi-supervised multi-class classification problem of learning from sparse labelled and abundant unlabelled training data.

General Classification Multi-class Classification +1

Deep Association Learning for Unsupervised Video Person Re-identification

1 code implementation22 Aug 2018 Yanbei Chen, Xiatian Zhu, Shaogang Gong

In this work, to address the video person re-id task, we formulate a novel Deep Association Learning (DAL) scheme, the first end-to-end deep learning method using none of the identity labels in model initialisation and training.

Unsupervised Person Re-Identification Video-Based Person Re-Identification

Person Search by Multi-Scale Matching

no code implementations ECCV 2018 Xu Lan, Xiatian Zhu, Shaogang Gong

In contrast to previous studies, we show that sufficiently reliable person instance cropping is achievable by slightly improved state-of-the-art deep learning object detectors (e. g. Faster-RCNN), and the under-studied multi-scale matching problem in person search is a more severe barrier.

Human Detection Person Search

Open Logo Detection Challenge

2 code implementations5 Jul 2018 Hang Su, Xiatian Zhu, Shaogang Gong

In this work, we introduce a more realistic and challenging logo detection setting, called Open Logo Detection.

Person Re-Identification in Identity Regression Space

no code implementations25 Jun 2018 Hanxiao Wang, Xiatian Zhu, Shaogang Gong, Tao Xiang

Most existing person re-identification (re-id) methods are unsuitable for real-world deployment due to two reasons: Unscalability to large population size, and Inadaptability over time.

Incremental Learning Person Re-Identification

Knowledge Distillation by On-the-Fly Native Ensemble

3 code implementations NeurIPS 2018 Xu Lan, Xiatian Zhu, Shaogang Gong

Knowledge distillation is effective to train small and generalisable network models for meeting the low-memory and fast running requirements.

Knowledge Distillation

Imbalanced Deep Learning by Minority Class Incremental Rectification

1 code implementation28 Apr 2018 Qi Dong, Shaogang Gong, Xiatian Zhu

In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, and ignore the challenge of learning from significantly imbalanced training data.

Facial Attribute Classification

Surveillance Face Recognition Challenge

1 code implementation25 Apr 2018 Zhiyi Cheng, Xiatian Zhu, Shaogang Gong

To facilitate more studies on developing FR models that are effective and robust for low-resolution surveillance facial images, we introduce a new Surveillance Face Recognition Challenge, which we call the QMUL-SurvFace benchmark.

Face Recognition

Scalable Deep Learning Logo Detection

2 code implementations30 Mar 2018 Hang Su, Shaogang Gong, Xiatian Zhu

Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world dynamic applications.

Incremental Learning

Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification

no code implementations CVPR 2018 Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li

Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair.

Unsupervised Domain Adaptation Unsupervised Person Re-Identification

Harmonious Attention Network for Person Re-Identification

1 code implementation CVPR 2018 Wei Li, Xiatian Zhu, Shaogang Gong

Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images.

Person Re-Identification

Class Rectification Hard Mining for Imbalanced Deep Learning

1 code implementation ICCV 2017 Qi Dong, Shaogang Gong, Xiatian Zhu

Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes.

Attribute Recognition by Joint Recurrent Learning of Context and Correlation

no code implementations ICCV 2017 Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li

Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small.

Multi-Label Image Classification Pedestrian Attribute Recognition

Deep Reinforcement Learning Attention Selection for Person Re-Identification

no code implementations10 Jul 2017 Xu Lan, Hanxiao Wang, Shaogang Gong, Xiatian Zhu

Existing person re-identification (re-id) methods assume the provision of accurately cropped person bounding boxes with minimum background noise, mostly by manually cropping.

Person Re-Identification reinforcement-learning

Discovering Visual Concept Structure with Sparse and Incomplete Tags

no code implementations30 May 2017 Jingya Wang, Xiatian Zhu, Shaogang Gong

As a result, our model is able to discover more accurate semantic correlation between textual tags and visual features, and finally providing favourable visual semantics interpretation even with highly sparse and incomplete tags.

TAG

Person Re-Identification by Deep Joint Learning of Multi-Loss Classification

no code implementations12 May 2017 Wei Li, Xiatian Zhu, Shaogang Gong

Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone.

feature selection General Classification +1

Person Re-Identification by Camera Correlation Aware Feature Augmentation

no code implementations26 Mar 2017 Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, Jian-Huang Lai

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion.

Person Re-Identification

Deep Learning Logo Detection with Data Expansion by Synthesising Context

no code implementations29 Dec 2016 Hang Su, Xiatian Zhu, Shaogang Gong

Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs.

Human-In-The-Loop Person Re-Identification

no code implementations5 Dec 2016 Hanxiao Wang, Shaogang Gong, Xiatian Zhu, Tao Xiang

Current person re-identification (re-id) methods assume that (1) pre-labelled training data are available for every camera pair, (2) the gallery size for re-identification is moderate.

Ensemble Learning Incremental Learning +1

Person Re-Identification by Unsupervised Video Matching

no code implementations25 Nov 2016 Xiaolong Ma, Xiatian Zhu, Shaogang Gong, Xudong Xie, Jianming Hu, Kin-Man Lam, Yisheng Zhong

Crucially, this model does not require pairwise labelled training data (i. e. unsupervised) therefore readily scalable to large scale camera networks of arbitrary camera pairs without the need for exhaustive data annotation for every camera pair.

Dynamic Time Warping Person Re-Identification +1

Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes

no code implementations12 Oct 2016 Qi Dong, Shaogang Gong, Xiatian Zhu

Recognising detailed clothing characteristics (fine-grained attributes) in unconstrained images of people in-the-wild is a challenging task for computer vision, especially when there is only limited training data from the wild whilst most data available for model learning are captured in well-controlled environments using fashion models (well lit, no background clutter, frontal view, high-resolution).

Transfer Learning

Person Re-Identification by Discriminative Selection in Video Ranking

no code implementations23 Jan 2016 Taiqing Wang, Shaogang Gong, Xiatian Zhu, Shengjin Wang

Current person re-identification (ReID) methods typically rely on single-frame imagery features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios.

Gait Recognition Person Re-Identification

Learning from Multiple Sources for Video Summarisation

no code implementations13 Jan 2015 Xiatian Zhu, Chen Change Loy, Shaogang Gong

Many visual surveillance tasks, e. g. video summarisation, is conventionally accomplished through analysing imagerybased features.

Video Understanding

Constructing Robust Affinity Graphs for Spectral Clustering

no code implementations CVPR 2014 Xiatian Zhu, Chen Change Loy, Shaogang Gong

Spectral clustering requires robust and meaningful affinity graphs as input in order to form clusters with desired structures that can well support human intuition.

Cannot find the paper you are looking for? You can Submit a new open access paper.