Search Results for author:
Found 146 papers, 64 papers with code
UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing
Human pose plays a crucial role in the digital age.
Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection
The primary goal of out-of-distribution (OOD) detection tasks is to identify inputs with semantic shifts, i. e., if samples from novel classes are absent in the in-distribution (ID) dataset used for training, we should reject these OOD samples rather than misclassifying them into existing ID classes.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
Under this unsupervised multi-domain setting, we have identified inherent model bias within CLIP, notably in its visual and text encoders.
CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
However, for every single condition type, ControlNet requires independent training on millions of data pairs with hundreds of GPU hours, which is quite expensive and makes it challenging for ordinary users to explore and develop new types of conditions.
HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding
The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centric scenarios.
Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models
Categorization, a core cognitive ability in humans that organizes objects based on common features, is essential to cognitive science as well as computer vision.
T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
In this paper, for the first time, we propose a comprehensive defense method named T2IShield to detect, localize, and mitigate such attacks.
Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
Besides, these benchmarks merely focus on evaluating LVLMs on the realistic style images and clean scenarios, leaving the multi-stylized images and noisy scenarios unexplored.
Evaluating the Quality of Hallucination Benchmarks for Large Vision-Language Models
Furthermore, based on the results of our quality measurement, we construct a High-Quality Hallucination Benchmark (HQH) for LVLMs, which demonstrates superior reliability and validity under our HQM framework.
VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence.
Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
In this paper, we construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue, in which we divide the test samples into subsets with different semantic and covariate shift degrees relative to the ID dataset.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
In this paper, we propose a novel SSL setting, where unlabeled samples are drawn from a mixed distribution that deviates from the feature distribution of labeled samples.
M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models
In this work, we introduce M4U, a novel and challenging benchmark for assessing the capability of multi-discipline multilingual multimodal understanding and reasoning.
Task-adaptive Q-Face
Although face analysis has achieved remarkable improvements in the past few years, designing a multi-task face analysis model is still challenging.
Quantitative Investment Diversification Strategies via Various Risk Models
This paper focuses on the developing of high-dimensional risk models to construct portfolios of securities in the US stock exchange.
Application of Deep Learning for Factor Timing in Asset Management
The paper examines the performance of regression models (OLS linear regression, Ridge regression, Random Forest, and Fully-connected Neural Network) on the prediction of CMA (Conservative Minus Aggressive) factor premium and the performance of factor timing investment with them.
Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relevant features.
HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention
The proposed Historical Prediction Attention together with the Agent Attention and Mode Attention is further formulated as the Triple Factorized Attention module, serving as the core design of HPNet. Experiments on the Argoverse and INTERACTION datasets show that HPNet achieves state-of-the-art performance, and generates accurate and stable future trajectories.
Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applications
In this paper, we try to understand FSL by delving into two key questions: (1) How to quantify the relationship between \emph{training} and \emph{novel} tasks?
Progressive Conservative Adaptation for Evolving Target Domains
Moreover, as adjusting to the most recent target domain can interfere with the features learned from previous target domains, we develop a conservative sparse attention mechanism.
Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement
The attention mechanism has been proven effective on various visual tasks in recent years.
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
Instead of that, we train an Encoder-Decoder to generate a set of dynamic event memories at the glancing stage.
Ranked #1 on
Video Question Answering
on AGQA 2.0 balanced
ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations
While many recent approaches for this task primarily rely on guiding the learning process using the audio modality alone to capture information shared between audio and video we reframe the problem as the acquisition of shared unique (modality-specific) and synergistic speech information to address the inherent asymmetry between the modalities.
Ranked #1 on
Audio-Visual Speech Recognition
on CAS-VSR-S101
Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues
By integrating cooperative dual attention in the visual encoder and audio-visual fusion strategy, our model effectively extracts beneficial speech information from both audio and visual cues for AVSE.
Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading
For deep layers where both the speaker's features and the speech content features are all expressed well, we introduce the speaker-adaptive features to learn for suppressing the speech content irrelevant noise for robust lip reading.
Dual Compensation Residual Networks for Class Imbalanced Learning
Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models.
BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task.
Function-Consistent Feature Distillation
The core idea of FCFD is to make teacher and student features not only numerically similar, but more importantly produce similar outputs when fed to the later part of the same network.
Diversity-Measurable Anomaly Detection
In this paper, to better handle the tradeoff problem, we propose Diversity-Measurable Anomaly Detection (DMAD) framework to enhance reconstruction diversity while avoid the undesired generalization on anomalies.
Ranked #1 on
Anomaly Detection
on UCSD Ped2
Anomaly Detection In Surveillance Videos
Defect Detection
+2
Source-Free Adaptive Gaze Estimation by Uncertainty Reduction
In light of this, we present an unsupervised source-free domain adaptation approach for gaze estimation, which adapts a source-trained gaze estimator to unlabeled target domains without source data.
DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization
Domain generalization (DG) attempts to learn a model on source domains that can well generalize to unseen but different domains.
CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition
The co-occurrence signals (e. g., hand shape, facial expression, and lip pattern) play a critical role in Continuous Sign Language Recognition (CSLR).
DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction
Then we propose a dynamic threshold strategy for each instance, based on the momentum of each instance's memorization strength in previous epochs to select and correct noisy labeled data.
Deep Radial Embedding for Visual Sequence Learning
The blank class of CTC plays a crucial role in the alignment process and is often considered responsible for the peaky behavior of CTC.
Clothes-Changing Person Re-identification with RGB Modality Only
In this paper, we propose a Clothes-based Adversarial Loss (CAL) to mine clothes-irrelevant features from the original RGB images by penalizing the predictive power of re-id model w. r. t.
Ranked #1 on
Multiview Gait Recognition
on CASIA-B
Clothes Changing Person Re-Identification
Multiview Gait Recognition
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability.
Ranked #4 on
Visual Tracking
on TNL2K
From Node to Graph: Joint Reasoning on Visual-Semantic Relational Graph for Zero-Shot Detection
Zero-Shot Detection (ZSD), which aims at localizing andrecognizing unseen objects in a complicated scene, usuallyleverages the visual and semantic information of individ-ual objects alone.
Ranked #6 on
Generalized Zero-Shot Object Detection
on MS-COCO
Generalized Zero-Shot Object Detection
Scene Understanding
+1
Salient-to-Broad Transition for Video Person Re-Identification
To further improve SBM, an Integration-and-Distribution Module (IDM) is introduced to enhance frame-level representations.
Enhancing Face Recognition With Self-Supervised 3D Reconstruction
In this paper, we propose to enhance face recognition with a bypass of self-supervised 3D reconstruction, which enforces the neural backbone to focus on the identity-related depth and albedo information while neglects the identity-irrelevant pose and illumination information.
HRFormer: High-Resolution Vision Transformer for Dense Predict
We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost.
SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning
However, human can learn new classes quickly even given few samples since human can tell what discriminative features should be focused on about each category based on both the visual and semantic prior knowledge.
HRFormer: High-Resolution Transformer for Dense Prediction
We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost.
Ranked #3 on
Pose Estimation
on AIC
UniCon: Unified Context Network for Robust Active Speaker Detection
Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties.
Active Speaker Detection
Audio-Visual Active Speaker Detection
Hierarchical Context-aware Network for Dense Video Event Captioning
Dense video event captioning aims to generate a sequence of descriptive captions for each event in a long untrimmed video.
Locality-aware Channel-wise Dropout for Occluded Face Recognition
Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area.
Gaze Estimation with an Ensemble of Four Architectures
This paper presents a method for gaze estimation according to face images.
Feature Completion for Occluded Person Re-Identification
Our method significantly outperforms existing methods on the occlusion datasets, while remains top even superior performance on holistic datasets.
FAIEr: Fidelity and Adequacy Ensured Image Caption Evaluation
Then for evaluating the adequacy of the candidate caption, it highlights the image gist on the visual scene graph under the guidance of the reference captions.
Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking
This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN), for visual object tracking.
Visual Alignment Constraint for Continuous Sign Language Recognition
Specifically, the proposed VAC comprises two auxiliary losses: one focuses on visual features only, and the other enforces prediction alignment between the feature extractor and the alignment module.
Ranked #11 on
Sign Language Recognition
on RWTH-PHOENIX-Weather 2014
Topic Scene Graph Generation by Attention Distillation From Caption
To this end, we let the scene graph borrow the ability from the image caption so that it can be a specialist on the basis of remaining all-around, resulting in the so-called Topic Scene Graph.
Env-QA: A Video Question Answering Benchmark for Comprehensive Understanding of Dynamic Environments
Visual understanding goes well beyond the study of images or videos on the web.
Self-Mutual Distillation Learning for Continuous Sign Language Recognition
Currently, a typical network combination for CSLR includes a visual module, which focuses on spatial and short-temporal information, followed by a contextual module, which focuses on long-temporal information, and the Connectionist Temporal Classification (CTC) loss is adopted to train the network.
Holistic Pose Graph: Modeling Geometric Structure Among Objects in a Scene Using Graph Inference for 3D Object Prediction
The inference of the HPG uses GRU to encode the pose features from their corresponding regions in a single RGB image, and passes messages along the graph structure iteratively to improve the predicted poses.
Cross-Encoder for Unsupervised Gaze Representation Learning
To address the issue that the feature of gaze is always intertwined with the appearance of the eye, Cross-Encoder disentangles the features using a latent-code-swapping mechanism on eye-consistent image pairs and gaze-similar ones.
Attributes Aware Face Generation with Generative Adversarial Networks
Recent studies have shown remarkable success in face image generations.
Learn an Effective Lip Reading Model without Pains
Considering the non-negligible effects of these strategies and the existing tough status to train an effective lip reading model, we perform a comprehensive quantitative study and comparative analysis, for the first time, to show the effects of several different choices for lip reading.
Ranked #2 on
Lipreading
on CAS-VSR-W1k (LRW-1000)
IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
Furthermore, a Channel IAU (CIAU) module is designed to model the semantic contextual interactions between channel features to enhance the feature representation, especially for small-scale visual cues and body parts.
Temporal Complementary Learning for Video Person Re-Identification
This paper proposes a Temporal Complementary Learning Network that extracts complementary features of consecutive video frames for video person re-identification.
Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation
Scene graph aims to faithfully reveal humans' perception of image content.
Appearance-Preserving 3D Convolution for Video-based Person Re-identification
Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID).
SegFix: Model-Agnostic Boundary Refinement for Segmentation
We present a model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model.
Synchronous Bidirectional Learning for Multilingual Lip Reading
Based on this idea, we try to explore the synergized learning of multilingual lip reading in this paper, and further propose a synchronous bidirectional learning (SBL) framework for effective synergy of multilingual lip reading.
Single-Side Domain Generalization for Face Anti-Spoofing
In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing.
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors.
Ranked #88 on
Object Detection
on COCO test-dev
(using extra training data)
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning
In light of this, we propose an efficient disentangled representation learning for cross-domain face PAD.
Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
Then, we introduce three aggregators which guide the message passing from one graph to another to utilize the contexts in various modalities, so as to refine the features of nodes.
Mutual Information Maximization for Effective Lip Reading
By combining these two advantages together, the proposed method is expected to be both discriminative and robust for effective lip reading.
Ranked #8 on
Lipreading
on CAS-VSR-W1k (LRW-1000)
Deformation Flow Based Two-Stream Network for Lip Reading
Observing on the continuity in adjacent frames in the speaking process, and the consistency of the motion patterns among different speakers when they pronounce the same phoneme, we model the lip movements in the speaking process as a sequence of apparent deformations in the lip region.
Ranked #7 on
Lipreading
on CAS-VSR-W1k (LRW-1000)
Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading
On the one hand, we introduce the evaluation metric (refers to the character error rate in this paper) as a form of reward to optimize the model together with the original discriminative target.
Ranked #9 on
Lipreading
on CAS-VSR-W1k (LRW-1000)
Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition
Recent advances in deep learning have heightened interest among researchers in the field of visual speech recognition (VSR).
Ranked #2 on
Lipreading
on GRID corpus (mixed-speech)
Emotion Recognition for In-the-wild Videos
This paper is a brief introduction to our submission to the seven basic expression classification track of Affective Behavior Analysis in-the-wild Competition held in conjunction with the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020.
$M^3$T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild
This report describes a multi-modal multi-task ($M^3$T) approach underlying our submission to the valence-arousal estimation track of the Affective Behavior Analysis in-the-wild (ABAW) Challenge, held in conjunction with the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020.
Deep Heterogeneous Hashing for Face Video Retrieval
To tackle the key challenge of hashing on the manifold, a well-studied Riemannian kernel mapping is employed to project data (i. e. covariance matrices) into Euclidean space and thus enables to embed the two heterogeneous representations into a common Hamming space, where both intra-space discriminability and inter-space compatibility are considered.
FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task Learning
Combined variations containing low-resolution and occlusion often present in face images in the wild, e. g., under the scenario of video surveillance.
Learning-based Real-time Detection of Intrinsic Reflectional Symmetry
In this paper, we propose \YL{a} learning-based approach to intrinsic reflectional symmetry detection.
LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
3D models are commonly used in computer vision and graphics.
RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representation
Recently, some methods have been proposed for remote HR estimation from face videos; however, most of them focus on well-controlled scenarios, their generalization ability into less-constrained scenarios (e. g., with head movement, and bad illumination) are not known.
Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition
In this work, we propose a semi-supervised approach for AU recognition utilizing a large number of web face images without AU labels and a relatively small face dataset with AU annotations inspired by the co-training methods.
Cross Attention Network for Few-shot Classification
The unseen classes and low-data problem make few-shot classification very challenging.
Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval
In the light of recent success of scene graph in many CV and NLP tasks for describing complex natural scenes, we propose to represent image and text with two kinds of scene graphs: visual scene graph (VSG) and textual scene graph (TSG), each of which is exploited to jointly characterize objects and relationships in the corresponding modality.
Hierarchical Disentangle Network for Object Representation Learning
In this paper, we propose the hierarchical disentangle network (HDN) to exploit the rich hierarchical characteristics among categories to divide the disentangling process in a coarse-to-fine manner, such that each level only focuses on learning the specific representations in its granularity and finally the common and unique representations in all granularities jointly constitute the raw object.
Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
We empirically demonstrate that the proposed approach achieves competitive performance on various challenging semantic segmentation benchmarks: Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff.
Ranked #5 on
Semantic Segmentation
on LIP val
Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation
This regularized CAM can be embedded in most recent advanced weakly supervised semantic segmentation framework.
Transferable Contrastive Network for Generalized Zero-Shot Learning
Zero-shot learning (ZSL) is a challenging problem that aims to recognize the target categories without seen data, where semantic information is leveraged to transfer knowledge from some source classes.
Ranked #7 on
Zero-Shot Learning
on SUN Attribute
Temporal Knowledge Propagation for Image-to-Video Person Re-identification
With back propagation, temporal knowledge can be transferred to enhance the image features and the information asymmetry problem can be alleviated.
Ranked #9 on
Person Re-Identification
on iLIDS-VID
CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense
To comprehensively evaluate such abilities, we propose a VQA benchmark, CRIC, which introduces new types of questions about Compositional Reasoning on vIsion and Commonsense, and an evaluation metric integrating the correctness of answering and commonsense grounding.
Interlaced Sparse Self-Attention for Semantic Segmentation
There are two successive attention modules each estimating a sparse affinity matrix.
Interaction-and-Aggregation Network for Person Re-identification
Person re-identification (reID) benefits greatly from deep convolutional neural networks (CNNs) which learn robust feature embeddings.
VRSTC: Occlusion-Free Video Person Re-Identification
For one thing, the spatial structure of a pedestrian frame can be used to predict the occluded body parts from the unoccluded body parts of this frame.
Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
Recent researches attempt to improve the detection performance by adopting the idea of cascade for single-stage detectors.
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information.
Weakly Supervised Object Detection with Segmentation Collaboration
Weakly supervised object detection aims at learning precise object detectors, given image category labels.
Fully Learnable Group Convolution for Acceleration of Deep Neural Networks
Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e. g. smartphone, embedded devices, etc.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning
To close the gap, we propose an efficient tattoo search approach that is able to learn tattoo detection and compact representation jointly in a single convolutional neural network (CNN) via multi-task learning.
LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild
It has shown a large variation in this benchmark in several aspects, including the number of samples in each class, video resolution, lighting conditions, and speakers' attributes such as pose, age, gender, and make-up.
Ranked #2 on
Lipreading
on LRW-1000
VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video
We also learn a deep HR estimator (named as RhythmNet) with the proposed spatial-temporal representation, which achieves promising results on both the public-domain and our VIPL-HR HR estimation databases.
Meta-Learning with Individualized Feature Space for Few-Shot Classification
Specifically, we introduce a kernel generator as meta-learner to learn to construct feature embedding for query images.
Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation
Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias.
OCNet: Object Context Network for Scene Parsing
To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling~\citep{zhao2017pyramid} and atrous spatial pyramid pooling~\citep{chen2018deeplab}.
Ranked #9 on
Semantic Segmentation
on Trans10K
Face Recognition with Contrastive Convolution
In current face recognition approaches with convolutional neural network (CNN), a pair of faces to compare are independently fed into the CNN for feature extraction.
Facial Expression Recognition with Inconsistently Annotated Datasets
To address the inconsistency, we propose an Inconsistent Pseudo Annotations to Latent Truth(IPA2LT) framework to train a FER model from multiple inconsistently labeled datasets and large scale unlabeled data.
Facial Expression Recognition
Facial Expression Recognition (FER)
Generative Adversarial Network with Spatial Attention for Face Attribute Editing
The generator contains an attribute manipulation network (AMN) to edit the face image, and a spatial attention network (SAN) to localize the attribute-specific region which restricts the alternation of AMN within this region.
Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition
Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets.
Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
Context is important for accurate visual recognition.
Duplex Generative Adversarial Network for Unsupervised Domain Adaptation
Following the similar idea of GAN, this work proposes a novel GAN architecture with duplex adversarial discriminators (referred to as DupGAN), which can achieve domain-invariant representation and domain transformation.
Mean-Variance Loss for Deep Age Estimation From a Face
Age estimation has broad application prospects of many fields, such as video surveillance, social networking, and human-computer interaction.
Ranked #3 on
Age Estimation
on ChaLearn 2016
Visual relationship detection with deep structural ranking
In this paper, we propose a novel framework, called Deep Structural Ranking, for visual relationship detection.
Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
Rotation-invariant face detection, i. e. detecting faces with arbitrary rotation-in-plane (RIP) angles, is widely required in unconstrained applications but still remains as a challenging task, due to the large variations of face appearances.
Texture Classification in Extreme Scale Variations using GANet
Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding we are developing a new dataset, the Extreme Scale Variation Textures (ESVaT), to test the performance of our framework.
AttGAN: Facial Attribute Editing by Only Changing What You Want
Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of the given face conditioned on the desired attributes.
Catadioptric HyperSpectral Light Field Imaging
In this paper, we present a single camera hyperspectral light field imaging solution that we call Snapshot Plenoptic Imager (SPI).
Learning Discriminative Latent Attributes for Zero-Shot Classification
Zero-shot learning (ZSL) aims to transfer knowledge from observed classes to the unseen classes, based on the assumption that both the seen and unseen classes share a common semantic space, among which attributes enjoy a great popularity.
Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition
The designed ReST has an intrinsic recursive structure and is capable of progressively aligning faces to a canonical one, even those with large variations.
Discriminative Covariance Oriented Representation Learning for Face Recognition With Image Sets
For face recognition with image sets, while most existing works mainly focus on building robust set models with hand-crafted feature, it remains a research gap to learn better image representations which can closely match the subsequent image set modeling and classification.
Learning Multifunctional Binary Codes for Both Category and Attribute Oriented Retrieval Tasks
In this paper we propose a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes.
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach
In DMTL, we tackle attribute correlation and heterogeneity with convolutional neural networks (CNNs) consisting of shared feature learning for all the attributes, and category-specific feature learning for heterogeneous attributes.
Ranked #5 on
Facial Attribute Classification
on LFWA
Funnel-Structured Cascade for Multi-View Face Detection with Alignment-Awareness
On the other hand, by using a unified MLP cascade to examine proposals of all views in a centralized style, it provides a favorable solution for multi-view face detection with high accuracy and low time-cost.
VIPLFaceNet: An Open Source Deep Face Recognition SDK
Robust face representation is imperative to highly accurate face recognition.
Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition
Specifically, by exploiting the Riemannian geometry of the manifold of fixed-rank Positive Semidefinite (PSD) matrices, we present a new solution to reduce optimizing over the space of column full-rank transformation matrices to optimizing on the PSD manifold which has a well-established Riemannian structure.
Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video
With this mapping, the problem of learning a cross-view metric between the two source heterogeneous spaces can be expressed as learning a single-view Euclidean distance metric in the target common Euclidean space.
Dual Purpose Hashing
Recent years have seen more and more demand for a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes.
Deep Supervised Hashing for Fast Image Retrieval
In this paper, we present a new hashing method to learn compact binary codes for highly efficient image retrieval on large-scale datasets.
Ranked #1 on
Image Retrieval
on CIFAR-10
Multi-View Deep Network for Cross-View Classification
As a result, the representation from the topmost layers of the MvDN network is robust to view discrepancy, and also discriminative.
Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders
Face alignment or facial landmark detection plays an important role in many computer vision applications, e. g., face recognition, facial expression recognition, face animation, etc.
A Unified Multiplicative Framework for Attribute Learning
Attributes are mid-level semantic properties of objects.
Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation
To alleviate the discrepancy between source and target domains, we propose a domain adaptation method, named as Bi-shifting Auto-Encoder network (BAE).
Leveraging Datasets With Varying Annotations for Face Alignment via Deep Regression Network
Facial landmark detection, as a vital topic in computer vision, has been studied for many decades and lots of datasets have been collected for evaluation.
Two Birds, One Stone: Jointly Learning Binary Code for Large-Scale Face Image Retrieval and Attributes Prediction
In this way, the learned binary codes can be applied to not only fine-grained face image retrieval, but also facial attributes prediction, which is the very innovation of this work, just like killing two birds with one stone.
Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition
3) the local modes on each STM can be instantiated by fitting to UMM, and the corresponding expressionlet is constructed by modeling the variations in each local mode.
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
Learning Mid-level Words on Riemannian Manifold for Action Recognition
Human action recognition remains a challenging task due to the various sources of video data and large intra-class variations.
AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation
Another key feature of the proposed AgeNet is that, to avoid the problem of over-fitting on small apparent age training set, we exploit a general-to-specific transfer learning scheme.
Ranked #4 on
Age Estimation
on ChaLearn 2015
Deep Trans-layer Unsupervised Networks for Representation Learning
Compared to traditional deep learning methods, the implemented feature learning method has much less parameters and is validated in several typical experiments, such as digit recognition on MNIST and MNIST variations, object recognition on Caltech 101 dataset and face verification on LFW dataset.
Cross-pose Face Recognition by Canonical Correlation Analysis
We argue that one of the diffculties in this problem is the severe misalignment in face images or feature vectors with different poses.
Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition With Image Sets
This paper presents a method named Discriminant Analysis on Riemannian manifold of Gaussian distributions (DARG) to solve the problem of face recognition with image sets.
Projection Metric Learning on Grassmann Manifold With Application to Video Based Face Recognition
In video based face recognition, great success has been made by representing videos as linear subspaces, which typically lie in a special type of non-Euclidean space known as Grassmann manifold.
Face Video Retrieval With Image Query via Hashing Across Euclidean Space and Riemannian Manifold
Retrieving videos of a specific person given his/her face image as query becomes more and more appealing for applications like smart movie fast-forwards and suspect searching.
Generalized Unsupervised Manifold Alignment
In this paper, we propose a generalized Unsupervised Manifold Alignment (GUMA) method to build the connections between different but correlated datasets without any known correspondences.
Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification
Since the points commonly lie in Euclidean space while the sets are typically modeled as elements on Riemannian manifold, they can be treated as Euclidean points and Riemannian points respectively.
Stacked Progressive Auto-Encoders (SPAE) for Face Recognition Across Poses
Identifying subjects with variations caused by poses is one of the most challenging tasks in face recognition, since the difference in appearances caused by poses may be even larger than the difference due to identity.
Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial Expression Recognition
In this paper, we attempt to solve both problems via manifold modeling of videos based on a novel mid-level representation, i. e. expressionlet.
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
Deeply Coupled Auto-encoder Networks for Cross-view Classification
In this paper, we propose a simple but effective coupled neural network, called Deeply Coupled Autoencoder Networks (DCAN), which seeks to build two deep neural networks, coupled with each other in every corresponding layers.
Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Spatial-Temporal Face Region Descriptor, STFRD) for images (resp.
