Search Results for author:
Found 99 papers, 24 papers with code
InvSeg: Test-Time Prompt Inversion for Semantic Segmentation
To solve this, we propose InvSeg, a test-time prompt inversion method that tackles open-vocabulary semantic segmentation by inverting image-specific visual context into text prompt embedding space, leveraging structure information derived from the diffusion model's reconstruction process to enrich text prompts so as to associate each class with a structure-consistent mask.
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
In this paper, we utilize hallucinations to mine task-related information from images and verify its accuracy for enhancing precision of the generated prompts.
Camouflaged Object Segmentation with a Single Task-generic Prompt
Medical Image Segmentation
+1
Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion
In the field of Few-Shot Image Generation (FSIG) using Deep Generative Models (DGMs), accurately estimating the distribution of target domain with minimal samples poses a significant challenge.
SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence.
MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval
This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text.
Hybrid-Learning Video Moment Retrieval across Multi-Domain Labels
Experiments show EVA's effectiveness in exploring temporal segment annotations in a source domain to help learn video moment retrieval without temporal labels in a target domain.
Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer
Current facial expression recognition (FER) models are often designed in a supervised learning manner and thus are constrained by the lack of large-scale facial expression images with high-quality annotations.
Generative Video Diffusion for Unseen Cross-Domain Video Moment Retrieval
We address two problems in video editing for optimising unseen domain VMR: (1) generation of high-quality simulation videos of different moments with subtle distinctions, (2) selection of simulation videos that complement existing source training videos without introducing harmful noise or unnecessary repetitions.
Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking
Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text.
Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects
In this work, we aim to eliminate the need for manual prompt.
Camouflaged Object Segmentation with a Single Task-generic Prompt
object-detection
+2
Benchmarking Robustness of Text-Image Composed Retrieval
In this paper, we perform the first robustness study and establish three new diversified benchmarks for systematic analysis of text-image composed retrieval against natural corruptions in both vision and text and further probe textural understanding.
Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID
While deep learning has significantly improved ReID model accuracy under the independent and identical distribution (IID) assumption, it has also become clear that such models degrade notably when applied to an unseen novel domain due to unpredictable/unknown domain shift.
GridCLIP: One-Stage Object Detection by Grid-Level CLIP Representation Learning
Specifically, GridCLIP performs Grid-level Alignment to adapt the CLIP image-level representations to grid-level representations by aligning to CLIP category representations to learn the annotated (especially frequent) categories.
3D Shape Temporal Aggregation for Video-Based Clothing-Change Person Re-Identication
However, existing Re-ID methods usually generate 3D body shapes without considering identity modeling, which severely weakens the discriminability of 3D human shapes.
Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training
The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding.
Clothing-Change Feature Augmentation for Person Re-Identification
Specifically, to formulate meaningful clothing variations in the feature space, our method first estimates a clothing-change normal distribution with intra-ID cross-clothing variances.
Exploring Semantic Attributes from A Foundation Model for Federated Learning of Disjoint Label Spaces
To resolve this problem, federated learning has been introduced to transfer knowledge across multiple sources (clients) with non-shared data while optimising a globally generalised central model (server).
Rapid Person Re-Identification via Sub-space Consistency Regularization
To strike a balance between the model accuracy and efficiency, we propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by $0. 25$ times than real-value features under the same dimensions whilst maintaining a competitive accuracy, especially under short codes.
Video Activity Localisation with Uncertainties in Temporal Boundary
Such uncertainties in temporal labelling are currently ignored in model training, resulting in learning mis-matched video-text correlation with poor generalisation in test.
Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i. e., biased domain adaptation.
Feature-Distribution Perturbation and Calibration for Generalized Person ReID
In this work, we propose a Feature-Distribution Perturbation and Calibration (PECA) method to derive generic feature representations for person ReID, which is not only discriminative across cameras but also agnostic and deployable to arbitrary unseen target domains.
A Framework of Meta Functional Learning for Regularising Knowledge Transfer
The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned.
Ranking Distance Calibration for Cross-Domain Few-Shot Learning
The calibrated distance in this target-aware non-linear subspace is complementary to that in the pre-trained representation.
Local-Global Associative Frame Assemble in Video Re-ID
In this work, we explore jointly both local alignments and global correlations with further consideration of their mutual promotion/reinforcement so to better assemble complementary discriminative Re-ID information within all the relevant frames in video tracklets.
Decentralised Person Re-Identification with Selective Knowledge Aggregation
This helps to preserve model personalisation knowledge on each local client domain and learn instance-specific information.
Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation
Video activity localisation has recently attained increasing attention due to its practical values in automatically localising the most salient visual segments corresponding to their language descriptions (sentences) from untrimmed and unstructured videos.
Deep Clustering by Semantic Contrastive Learning
Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less well understood.
Unsupervised Noisy Tracklet Person Re-identification
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.
Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation
Our base model consists of a domain-invariant feature extractor and an ensemble of domain-specific classifiers.
Domain Generalization
Multi-Source Unsupervised Domain Adaptation
+1
Fewmatch: Dynamic Prototype Refinement for Semi-Supervised Few-Shot Learning
Semi-Supervised Few-shot Learning (SS-FSL) investigates the benefit of incorporating unlabelled data in few-shot settings.
Striking a Balance Between Stability and Plasticity for Class-Incremental Learning
With the reformulated baseline, we present two new approaches to CIL by learning class-independent knowledge and multi-perspective knowledge, respectively.
A Simple Feature Augmentation for Domain Generalization
The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.
Faster Person Re-Identification
In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy.
Transfer Learning for Protein Structure Classification at Low Resolution
Structure determination is key to understanding protein function at a molecular level.
Unsupervised Transfer Learning with Self-Supervised Remedy
In this work, we address this problem by transfer clustering that aims to learn a discriminative latent space of the unlabelled target data in a novel domain by knowledge transfer from labelled related domains.
Peer Collaborative Learning for Online Knowledge Distillation
Meanwhile, we employ the temporal mean model of each peer as the peer mean teacher to collaboratively transfer knowledge among peers, which helps each peer to learn richer knowledge and facilitates to optimise a more stable model with better generalisation.
Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification
Specifically, each local client receives global model updates from the server and trains a local model using its local data independent from all the other clients.
Intra-Camera Supervised Person Re-Identification
Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data.
Characteristic Regularisation for Super-Resolving Face Images
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.
Neural Operator Search
We address this limitation by additionally exploiting feature self-calibration operations, resulting in a heterogeneous search space.
Intra-Camera Supervised Person Re-Identification: A New Benchmark
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.
Zero-Shot Crowd Behavior Recognition
To that end, we relax the common assumption that each individual crowd video instance is only associated with a single crowd attribute.
Universal Person Re-Identification
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.
Unsupervised Deep Learning by Neighbourhood Discovery
Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations.
Unsupervised Person Re-identification by Soft Multilabel Learning
To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID.
Ranked #83 on
Person Re-Identification
on DukeMTMC-reID
Unsupervised Tracklet Person Re-Identification
We formulate an Unsupervised Tracklet Association Learning (UTAL) framework.
Ranked #1 on
Person Re-Identification
on DukeTracklet
Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network
Additionally, to study the tasks of sketch-based hairstyle retrieval, this paper contributes a new instance-level photo-sketch dataset - Hairstyle Photo-Sketch dataset, which is composed of 3600 sketches and photos, and 2400 sketch-photo pairs.
Low-Resolution Face Recognition
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.
Single-Label Multi-Class Image Classification by Deep Logistic Regression
The objective learning formulation is essential for the success of convolutional neural networks.
Self-Referenced Deep Learning
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.
Vehicle Re-Identification in Context
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.
Unsupervised Person Re-identification by Deep Learning Tracklet Association
Mostexistingpersonre-identification(re-id)methods relyon supervised model learning on per-camera-pair manually labelled pairwise training data.
Ranked #2 on
Person Re-Identification
on DukeTracklet
Semi-Supervised Deep Learning with Memory
We consider the semi-supervised multi-class classification problem of learning from sparse labelled and abundant unlabelled training data.
Deep Association Learning for Unsupervised Video Person Re-identification
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.
Ranked #6 on
Person Re-Identification
on PRID2011
Unsupervised Person Re-Identification
Video-Based Person Re-Identification
Person Search by Multi-Scale Matching
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.
Open Logo Detection Challenge
In this work, we introduce a more realistic and challenging logo detection setting, called Open Logo Detection.
Person Re-Identification in Identity Regression Space
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.
Knowledge Distillation by On-the-Fly Native Ensemble
Knowledge distillation is effective to train small and generalisable network models for meeting the low-memory and fast running requirements.
Imbalanced Deep Learning by Minority Class Incremental Rectification
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.
Surveillance Face Recognition Challenge
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.
Scalable Deep Learning Logo Detection
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.
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
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.
Ranked #23 on
Unsupervised Domain Adaptation
on Market to Duke
Harmonious Attention Network for Person Re-Identification
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.
Ranked #13 on
Person Re-Identification
on CUHK03 detected
Class Rectification Hard Mining for Imbalanced Deep Learning
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.
Recent Advances in Zero-shot Recognition
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data.
RGB-Infrared Cross-Modality Person Re-Identification
To that end, matching RGB images with infrared images is required, which are heterogeneous with very different visual characteristics.
Ranked #4 on
Cross-Modal Person Re-Identification
on SYSU-MM01
(mAP (All-search & Single-shot) metric)
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
Attribute Recognition by Joint Recurrent Learning of Context and Correlation
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.
Deep Reinforcement Learning Attention Selection for Person Re-Identification
Existing person re-identification (re-id) methods assume the provision of accurately cropped person bounding boxes with minimum background noise, mostly by manually cropping.
Actor-Critic Sequence Training for Image Captioning
Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing.
Discovering Visual Concept Structure with Sparse and Incomplete Tags
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.
Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone.
Ranked #102 on
Person Re-Identification
on Market-1501
Semantic Autoencoder for Zero-Shot Learning
We show that with this additional reconstruction constraint, the learned projection function from the seen classes is able to generalise better to the new unseen classes.
Deep Learning Logo Detection with Data Expansion by Synthesising Context
Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs.
Highly Efficient Regression for Scalable Person Re-Identification
Existing person re-identification models are poor for scaling up to large data required in real-world applications due to: (1) Complexity: They employ complex models for optimal performance resulting in high computational cost for training at a large scale; (2) Inadaptability: Once trained, they are unsuitable for incremental update to incorporate any new data available.
Human-In-The-Loop Person Re-Identification
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.
Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
In this work, we improve the ability of ZSL to generalise across this domain shift in both model- and data-centric ways by formulating a visual-semantic mapping with better generalisation properties and a dynamic data re-weighting method to prioritise auxiliary data that are relevant to the target classes.
Ranked #7 on
Zero-Shot Action Recognition
on Olympics
Person Re-Identification by Unsupervised Video Matching
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.
Learning a Deep Embedding Model for Zero-Shot Learning
In this paper we argue that the key to make deep ZSL models succeed is to choose the right embedding space.
Ranked #16 on
Zero-Shot Action Recognition
on Kinetics
Deep Learning Prototype Domains for Person Re-Identification
Person re-identification (re-id) is the task of matching multiple occurrences of the same person from different cameras, poses, lighting conditions, and a multitude of other factors which alter the visual appearance.
Ranked #5 on
Person Re-Identification
on CUHK-SYSU
Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes
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).
Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification
Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training.
Learning a Discriminative Null Space for Person Re-identification
Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views.
Ranked #118 on
Person Re-Identification
on Market-1501
Person Re-Identification by Discriminative Selection in Video Ranking
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.
Partial Person Re-Identification
We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views.
Multi-Scale Learning for Low-Resolution Person Re-Identification
In real world person re-identification (re-id), images of people captured at very different resolutions from different locations need be matched.
Unsupervised Domain Adaptation for Zero-Shot Learning
Zero-shot learning (ZSL) can be considered as a special case of transfer learning where the source and target domains have different tasks/label spaces and the target domain is unlabelled, providing little guidance for the knowledge transfer.
Transductive Zero-Shot Action Recognition by Word-Vector Embedding
This is a more challenging problem than existing ZSL of still images and/or attributes, because the mapping between video spacetime features of actions and the semantic space is more complex and harder to learn for the purpose of generalising over any cross-category domain shift.
Free-hand Sketch Synthesis with Deformable Stroke Models
We present a generative model which can automatically summarize the stroke composition of free-hand sketches of a given category.
Discovery of Shared Semantic Spaces for Multi-Scene Video Query and Summarization
The growing rate of public space CCTV installations has generated a need for automated methods for exploiting video surveillance data including scene understanding, query, behaviour annotation and summarization.
Transductive Multi-class and Multi-label Zero-shot Learning
Recently, zero-shot learning (ZSL) has received increasing interest.
Transductive Multi-label Zero-shot Learning
Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems.
Semantic Embedding Space for Zero-Shot Action Recognition
In this framework a mapping is constructed between visual features and a human interpretable semantic description of each category, allowing categories to be recognised in the absence of any training data.
Ranked #34 on
Zero-Shot Action Recognition
on UCF101
Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels
In this paper, we propose a more principled way to identify annotation outliers by formulating the subjective visual property prediction task as a unified robust learning to rank problem, tackling both the outlier detection and learning to rank jointly.
Transductive Multi-view Zero-Shot Learning
A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and is applied without adaptation to the target dataset.
Learning from Multiple Sources for Video Summarisation
Many visual surveillance tasks, e. g. video summarisation, is conventionally accomplished through analysing imagerybased features.
Semantic Graph for Zero-Shot Learning
Specifically, in contrast to previous work which ignores the semantic relationships between seen classes and focus merely on those between seen and unseen classes, in this paper a novel approach based on a semantic graph is proposed to represent the relationships between all the seen and unseen class in a semantic word space.
Constructing Robust Affinity Graphs for Spectral Clustering
Spectral clustering requires robust and meaningful affinity graphs as input in order to form clusters with desired structures that can well support human intuition.
Cumulative Attribute Space for Age and Crowd Density Estimation
A number of computer vision problems such as human age estimation, crowd density estimation and body/face pose (view angle) estimation can be formulated as a regression problem by learning a mapping function between a high dimensional vector-formed feature input and a scalarvalued output.
