Search Results for author:
Found 125 papers, 54 papers with code
Dual Illumination Estimation for Robust Exposure Correction
By performing dual illumination estimation, we obtain two intermediate exposure correction results for the input image, with one fixes the underexposed regions and the other one restores the overexposed regions.
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 #80 on
Person Re-Identification
on DukeMTMC-reID
DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation
Text-to-3D generation, which synthesizes 3D assets according to an overall text description, has significantly progressed.
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations.
DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition
In this work, we explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field.
Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video.
Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
Secondly, the Conditional Feature Embedding requires the overall feature of a query image to be dynamically adjusted based on the gallery image it matches, while most of the existing methods ignore the reference images.
Ranked #1 on
Person Re-Identification
on CUHK03-C
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch.
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person's 3D shape.
Ranked #4 on
Person Re-Identification
on PRCC
Weakly supervised discriminative feature learning with state information for person identification
We evaluate our model on unsupervised person re-identification and pose-invariant face recognition.
AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection
Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data.
Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images
In this paper, we present a study using deep fully convolutional network and ensemble models to automatically detect such WMH using fluid attenuation inversion recovery (FLAIR) and T1 magnetic resonance (MR) scans.
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual.
Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
In this work, we argue that the features extracted from the pretrained extractor, e. g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy.
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Cross-modal Consensus Network forWeakly Supervised Temporal Action Localization
In this work, we argue that the features extracted from the pretrained extractor, e. g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical.
Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification
Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level.
Ranked #5 on
Person Re-Identification
on Market-1501
(using extra training data)
Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases
In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge.
Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification
To this end, we propose shape-erased feature learning paradigm that decorrelates modality-shared features in two orthogonal subspaces.
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Universal image restoration is a practical and potential computer vision task for real-world applications.
Squeeze-and-Attention Networks for Semantic Segmentation
The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features.
Ranked #6 on
Semantic Segmentation
on PASCAL VOC 2012 test
AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection
Critically, in FSDAOD, the data-scarcity in the target domain leads to an extreme data imbalance between the source and target domains, which potentially causes over-adaptation in traditional feature alignment.
A Versatile Framework for Multi-scene Person Re-identification
To overcome significant variations between images across camera views, mountains of variants of ReID models were developed for solving a number of challenges, such as resolution change, clothing change, occlusion, modality change, and so on.
Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training.
Ranked #117 on
Person Re-Identification
on Market-1501
SIOD: Single Instance Annotated Per Category Per Image for Object Detection
Object detection under imperfect data receives great attention recently.
Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric.
Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training
The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem.
Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
To learn camera-invariant representation from cross-camera unpaired training data, we propose a cross-camera feature prediction method to mine cross-camera self supervision information from camera-specific feature distribution by transforming fake cross-camera positive feature pairs and minimize the distances of the fake pairs.
ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation
We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors.
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i. e., aligning point cloud representation to image and text embedding space individually.
Ranked #1 on
Zero-shot 3D classification
on Objaverse LVIS
(using extra training data)
Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos
However, most existing works focus only on video dynamic information (i. e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos.
Ranked #2 on
Action Quality Assessment
on Rhythmic Gymnastic
Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data
The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks.
MIXGAN: Learning Concepts from Different Domains for Mixture Generation
In this work, we present an interesting attempt on mixture generation: absorbing different image concepts (e. g., content and style) from different domains and thus generating a new domain with learned concepts.
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining
However, existing prompt-based methods heavily rely on strong pretraining (typically trained on ImageNet-21k), and we find that their models could be trapped if the potential gap between the pretraining task and unknown future tasks is large.
Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition
To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a comprehensive evaluation of five state-of-the-art CLIP-based video learners under various types of domain gaps.
Human Co-Parsing Guided Alignment for Occluded Person Re-identification
Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results.
Ranked #3 on
Person Re-Identification
on Occluded-DukeMTMC
Person Re-identification by Contour Sketch under Moderate Clothing Change
Substantial development of re-id has recently been observed, and the majority of existing models are largely dependent on color appearance and assume that pedestrians do not change their clothes across camera views.
Discriminator-Free Generative Adversarial Attack
The Deep Neural Networks are vulnerable toadversarial exam-ples(Figure 1), making the DNNs-based systems collapsed byadding the inconspicuous perturbations to the images.
NECA: Neural Customizable Human Avatar
The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering.
Combined Depth Space based Architecture Search For Person Re-identification
We propose a novel search space called Combined Depth Space (CDS), based on which we search for an efficient network architecture, which we call CDNet, via a differentiable architecture search algorithm.
Adaptive Interaction Modeling via Graph Operations Search
We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling.
Cross-Camera Trajectories Help Person Retrieval in a Camera Network
To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information.
SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks
The SNN2ANN consists of 2 components: a) a weight sharing architecture between ANN and SNN and b) spiking mapping units.
Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography
Compared to supervised learning with labelled disease EEG data which can train a model to analyze specific diseases but would fail to monitor previously unseen statuses, anomaly detection based on only normal EEGs can detect any potential anomaly in new EEGs.
Weakly Supervised Text-Based Person Re-Identification
Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances.
Multimodal Action Quality Assessment
To leverage multimodal information for AQA, i. e., RGB, optical flow and audio information, we propose a Progressive Adaptive Multimodal Fusion Network (PAMFN) that separately models modality-specific information and mixed-modality information.
Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection
Important people detection is to automatically detect the individuals who play the most important roles in a social event image, which requires the designed model to understand a high-level pattern.
Revisit PCA-based Technique for Out-of-Distribution Detection
Out-of-distribution (OOD) detection is a desired ability to ensure the reliability and safety of intelligent systems.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment
Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions).
Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
Human motion prediction aims at generating future frames of human motion based on an observed sequence of skeletons.
A Coordinate-wise Optimization Algorithm for Sparse Inverse Covariance Selection
Sparse inverse covariance selection is a fundamental problem for analyzing dependencies in high dimensional data.
Deep CNNs for HEp-2 Cells Classification : A Cross-specimen Analysis
Automatic classification of Human Epithelial Type-2 (HEp-2) cells staining patterns is an important and yet a challenging problem.
Adversarial Attribute-Image Person Re-identification
While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image matching task.
One-pass Person Re-identification by Sketch Online Discriminant Analysis
While there is a few work on discussing online re-id, most of them require considerable storage of all passed data samples that have been ever observed, and this could be unrealistic for processing data from a large camera network.
PersonRank: Detecting Important People in Images
Always, some individuals in images are more important/attractive than others in some events such as presentation, basketball game or speech.
Latent Embeddings for Collective Activity Recognition
Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene.
Online Hashing
Specifically, a new loss function is proposed to measure the similarity loss between a pair of data samples in hamming space.
Robust Depth-based Person Re-identification
More specifically, we exploit depth voxel covariance descriptor and further propose a locally rotation invariant depth shape descriptor called Eigen-depth feature to describe pedestrian body shape.
Person Re-Identification by Camera Correlation Aware Feature Augmentation
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.
Embedding Deep Metric for Person Re-identication A Study Against Large Variations
From this point of view, selecting suitable positive i. e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations.
Top-push Video-based Person Re-identification
Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the occlusion, pose and camera-view change, and lighting variation problems.
An Enhanced Deep Feature Representation for Person Re-identification
In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features.
Human Re-identification by Matching Compositional Template with Cluster Sampling
This paper aims at a newly raising task in visual surveillance: re-identifying people at a distance by matching body information, given several reference examples.
Adversarial Open-World Person Re-Identification
The main idea is learning to attack feature extractor on the target people by using GAN to generate very target-like images (imposters), and in the meantime the model will make the feature extractor learn to tolerate the attack by discriminative learning so as to realize group-based verification.
Improving Fast Segmentation With Teacher-student Learning
Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks.
Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling
Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student.
Group-Attention Single-Shot Detector (GA-SSD): Finding Pulmonary Nodules in Large-Scale CT Images
In this paper, we propose a novel and effective abnormality detector implementing the attention mechanism and group convolution on 3D single-shot detector (SSD) called group-attention SSD (GA-SSD).
Computed Tomography (CT)
Finding Pulmonary Nodules In Large-Scale Ct Images
Deep Bilinear Learning for RGB-D Action Recognition
In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition.
A Matrix Splitting Method for Composite Function Minimization
Incorporating a new Gaussian elimination procedure, the matrix splitting method achieves state-of-the-art performance.
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.
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.
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
A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem
The sparse generalized eigenvalue problem arises in a number of standard and modern statistical learning models, including sparse principal component analysis, sparse Fisher discriminant analysis, and sparse canonical correlation analysis.
Numerical Analysis
Pedestrian re-identification based on Tree branch network with local and global learning
Deep part-based methods in recent literature have revealed the great potential of learning local part-level representation for pedestrian image in the task of person re-identification.
Weakly Supervised Person Re-Identification
In the conventional person re-id setting, it is assumed that the labeled images are the person images within the bounding box for each individual; this labeling across multiple nonoverlapping camera views from raw video surveillance is costly and time-consuming.
Learning to Learn Relation for Important People Detection in Still Images
In this work, we propose a deep imPOrtance relatIon NeTwork (POINT) that combines both relation modeling and feature learning.
A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition
Besides, we propose a View-guided Skeleton CNN (VS-CNN) to tackle the problem of arbitrary-view action recognition.
Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration
Thus, it is meaningful to let partially labeled domains learn from each other to classify all the unlabeled samples in each domain under an open-set setting.
Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks
Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential.
Deep Dual Relation Modeling for Egocentric Interaction Recognition
To exploit the strong relations for egocentric interaction recognition, we introduce a dual relation modeling framework which learns to model the relations between the camera wearer and the interactor based on the individual action representations of the two persons.
Cross-view Relation Networks for Mammogram Mass Detection
Mammogram is the most effective imaging modality for the mass lesion detection of breast cancer at the early stage.
Enhancing Underexposed Photos using Perceptually Bidirectional Similarity
To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency.
Jointly learning heterogeneous features for rgb-d activity recognition
The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets.
Ranked #8 on
Skeleton Based Action Recognition
on SYSU 3D
Early action prediction by soft regression
Our formulation of soft regression framework 1) overcomes a usual assumption in existing early action prediction systems that the progress level of on-going sequence is given in the testing stage; and 2) presents a theoretical framework to better resolve the ambiguity and uncertainty of subsequences at early performing stage.
Ranked #70 on
Skeleton Based Action Recognition
on NTU RGB+D 120
DSRGAN: Explicitly Learning Disentangled Representation of Underlying Structure and Rendering for Image Generation without Tuple Supervision
We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision.
Batch Face Alignment using a Low-rank GAN
This paper studies the problem of aligning a set of face images of the same individual into a normalized image while removing the outliers like partial occlusion, extreme facial expression as well as significant illumination variation.
Weakly Supervised Tracklet Person Re-Identification by Deep Feature-wise Mutual Learning
The scalability problem caused by the difficulty in annotating Person Re-identification(Re-ID) datasets has become a crucial bottleneck in the development of Re-ID. To address this problem, many unsupervised Re-ID methods have recently been proposed. Nevertheless, most of these models require transfer from another auxiliary fully supervised dataset, which is still expensive to obtain. In this work, we propose a Re-ID model based on Weakly Supervised Tracklets(WST) data from various camera views, which can be inexpensively acquired by combining the fragmented tracklets of the same person in the same camera view over a period of time. We formulate our weakly supervised tracklets Re-ID model by a novel method, named deep feature-wise mutual learning(DFML), which consists of Mutual Learning on Feature Extractors (MLFE) and Mutual Learning on Feature Classifiers (MLFC). We propose MLFE by leveraging two feature extractors to learn from each other to extract more robust and discriminative features. On the other hand, we propose MLFC by adapting discriminative features from various camera views to each classifier.
MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection
We address the weakly supervised video highlight detection problem for learning to detect segments that are more attractive in training videos given their video event label but without expensive supervision of manually annotating highlight segments.
An Asymmetric Modeling for Action Assessment
However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e. g., between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions.
Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
However, previous graph models regard human and object as the same kind of nodes and do not consider that the messages are not equally the same between different entities.
Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images.
Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors
In order to reduce the forgetting of particularly earlier learned old knowledge and improve the overall continual learning performance, we propose a simple yet effective fusion mechanism by including all the previously learned feature extractors into the intelligent model.
Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task.
Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-Identification
Recently, person re-identification (Re-ID) has achieved great progress.
Ranked #3 on
Person Re-Identification
on PRCC
Graph-Based High-Order Relation Modeling for Long-Term Action Recognition
In this paper, we propose a Graph-based High-order Relation Modeling (GHRM) module to exploit the high-order relations in the long-term actions for long-term action recognition.
Ranked #5 on
Video Classification
on Breakfast
Discriminative Distillation to Reduce Class Confusion in Continual Learning
Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects.
Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images
In this paper, a simple yet effective optimization method is proposed to interpret the activation of any kernel of interest in CNN models.
Learning To Know Where To See: A Visibility-Aware Approach for Occluded Person Re-Identification
Several mainstream methods utilize extra cues (e. g., human pose information) to distinguish human parts from obstacles to alleviate the occlusion problem.
Predictive Feature Learning for Future Segmentation Prediction
In the latent feature learned by the autoencoder, global structures are enhanced and local details are suppressed so that it is more predictive.
Action-guided 3D Human Motion Prediction
The ability of forecasting future human motion is important for human-machine interaction systems to understand human behaviors and make interaction.
Letter-level Online Writer Identification
To make the application of writer-id more practical (e. g., on mobile devices), we focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues.
Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition
The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e. g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN).
Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor
In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases.
Likert Scoring With Grade Decoupling for Long-Term Action Assessment
Long-term action quality assessment is a task of evaluating how well an action is performed, namely, estimating a quality score from a long video.
Ranked #1 on
Action Quality Assessment
on Rhythmic Gymnastic
Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning
Accordingly, we first exclude these surely non-existent categories by a complementary learning loss.
STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding
The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances.
Ranked #2 on
Spatio-Temporal Video Grounding
on HC-STVG2
PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification
For the class-center involved triplet loss, the positive and negative samples in each triplet are replaced by their corresponding class centers, which enforces data representations of the same class closer to the class center.
Learning Discriminative Representation via Metric Learning for Imbalanced Medical Image Classification
Data imbalance between common and rare diseases during model training often causes intelligent diagnosis systems to have biased predictions towards common diseases.
Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval
To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features.
Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning
The first one is to adaptively integrate multiple levels of old knowledge and transfer it to each block level in the new model.
PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
In this work, we propose a ladder self-attention block with multiple branches and a progressive shift mechanism to develop a light-weight transformer backbone that requires less computing resources (e. g. a relatively small number of parameters and FLOPs), termed Progressive Shift Ladder Transformer (PSLT).
Pyramid Texture Filtering
We present a simple but effective technique to smooth out textures while preserving the prominent structures.
Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding
The static stream performs cross-modal understanding in a single frame and learns to attend to the target object spatially according to intra-frame visual cues like object appearances.
Generating Anomalies for Video Anomaly Detection With Prompt-Based Feature Mapping
There also exists a scene gap between virtual and real scenarios, including scene-specific anomalies (events that are abnormal in one scene but normal in another) and scene-specific attributes, such as the viewpoint of the surveillance camera.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding
Specifically, we develop a hierarchical encoder that encodes the multi-modal inputs into semantics-aligned representations at different levels.
Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition
The CARE framework needs bounding boxes to represent the lesion regions of rare diseases.
Event-Guided Procedure Planning from Instructional Videos with Text Supervision
In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state.
DiffuVolume: Diffusion Model for Volume based Stereo Matching
Our method, termed DiffuVolume, considers the diffusion model as a cost volume filter, which will recurrently remove the redundant information from the cost volume.
Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling
Our idea for modeling Continual-AQA is to sequentially learn a task-consistent score-discriminative feature distribution, in which the latent features express a strong correlation with the score labels regardless of the task or action types.
Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval
In this work, we show the discrepancy between image-to-text association and text-to-image association and propose CADA: Cross-Modal Adaptive Dual Association that finely builds bidirectional image-text detailed associations.
Ranked #1 on
Text based Person Retrieval
on RSTPReid
(mAP metric)
Transformer for Object Re-Identification: A Survey
Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from varying viewpoints.
ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition
With the proposed ActionHub dataset, we further propose a novel Cross-modality and Cross-action Modeling (CoCo) framework for ZSAR, which consists of a Dual Cross-modality Alignment module and a Cross-action Invariance Mining module.
Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding
Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG.
Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels
This paper focuses on open-ended video question answering, which aims to find the correct answers from a large answer set in response to a video-related question.
