Search Results for author:
Found 93 papers, 48 papers with code
SSCGAN: Facial Attribute Editing via Style Skip Connections
Each connection extracts the style feature of the latent feature maps in the encoder and then performs a residual learning based mapping function in the global information space guided by the target attributes.
Enabling Deep Residual Networks for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has attracted extensive research attention due to its great flexibility of exploiting large-scale image-level annotation for detector training.
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost.
Differentiated Relevances Embedding for Group-based Referring Expression Comprehension
In particular, based on the visual and textual semantic features, RMSL conducts an adaptive learning cycle upon triplet ranking, where (1) the target-negative region-expression pairs with low within-group relevances are used preferentially in model training to distinguish the primary semantics of the target objects, and (2) an across-group relevance regularization is integrated into model training to balance the bias of group priority.
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
We demonstrate that both temporal grains are beneficial to atomic action recognition.
Towards Language-guided Visual Recognition via Dynamic Convolutions
Based on the LaConv module, we further build the first fully language-driven convolution network, termed as LaConvNet, which can unify the visual recognition and multi-modal reasoning in one forward structure.
Transformer-based Dual Relation Graph for Multi-label Image Recognition
Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i. e., structural relation graph and semantic relation graph.
Spatiotemporal Inconsistency Learning for DeepFake Video Detection
To address this issue, we term this task as a Spatial-Temporal Inconsistency Learning (STIL) process and instantiate it into a novel STIL block, which consists of a Spatial Inconsistency Module (SIM), a Temporal Inconsistency Module (TIM), and an Information Supplement Module (ISM).
Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing
However, little attention has been paid to the feature extraction process for the FAS task, especially the influence of normalization, which also has a great impact on the generalization of the learned representation.
Distributed Attention for Grounded Image Captioning
We study the problem of weakly supervised grounded image captioning.
Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework
In this paper, we propose a purely point-based framework for joint crowd counting and individual localization.
Ranked #1 on
Crowd Counting
on ShanghaiTech A
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.
Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification
In this paper, we propose a joint Modality and Pattern Alignment Network (MPANet) to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.
Graph-Based High-Order Relation Discovery for Fine-Grained Recognition
Fine-grained object recognition aims to learn effective features that can identify the subtle differences between visually similar objects.
Ranked #27 on
Fine-Grained Image Classification
on CUB-200-2011
Learning To Restore Hazy Video: A New Real-World Dataset and a New Method
On the other hand, the video dehazing algorithms, which can acquire more satisfying dehazing results by exploiting the temporal redundancy from neighborhood hazy frames, receive less attention due to the absence of the video dehazing datasets.
RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words
Then, we build a BERTbased language model to extract language context and propose Adaptive-Attention (AA) module on top of a transformer decoder to adaptively measure the contribution of visual and language cues before making decisions for word prediction.
Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation
To date, learning weakly supervised panoptic segmentation (WSPS) with only image-level labels remains unexplored.
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
In this work, we propose a high fidelity face swapping method, called HifiFace, which can well preserve the face shape of the source face and generate photo-realistic results.
Ranked #6 on
Face Swapping
on FaceForensics++
Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions.
Consistent Instance False Positive Improves Fairness in Face Recognition
Then, an additional penalty term, which is in proportion to the ratio of instance FPR overall FPR, is introduced into the denominator of the softmax-based loss.
Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.
Adaptive Feature Alignment for Adversarial Training
Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.
Auxiliary learning induced graph convolutional networks
In this article, we propose a novel auxiliary learning induced graph convolutional network in a multi-task fashion.
Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing
Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios.
Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #18 on
Instance Segmentation
on COCO test-dev
Delving into Data: Effectively Substitute Training for Black-box Attack
Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models.
Carrying out CNN Channel Pruning in a White Box
Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w. r. t.
Learning Dynamic Alignment via Meta-filter for Few-shot Learning
Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.
On Evolving Attention Towards Domain Adaptation
However, considering that the configuration of attention, i. e., the type and the position of attention module, affects the performance significantly, it is more generalized to optimize the attention configuration automatically to be specialized for arbitrary UDA scenario.
Ranked #1 on
Unsupervised Domain Adaptation
on Duke to Market
Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
Temporal action localization is an important yet challenging task in video understanding.
Learning Comprehensive Motion Representation for Action Recognition
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame.
Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network.
Image-to-image Translation via Hierarchical Style Disentanglement
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks.
Disentanglement
Multimodal Unsupervised Image-To-Image Translation
+1
Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query
However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description.
DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection.
Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System
Face authentication on mobile end has been widely applied in various scenarios.
Network Pruning using Adaptive Exemplar Filters
Inspired by the face recognition community, we use a message passing algorithm Affinity Propagation on the weight matrices to obtain an adaptive number of exemplars, which then act as the preserved filters.
Dual-Level Collaborative Transformer for Image Captioning
Descriptive region features extracted by object detection networks have played an important role in the recent advancements of image captioning.
Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation
Weakly supervised instance segmentation (WSIS) with only image-level labels has recently drawn much attention.
Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework
In this paper, we propose a purely point-based framework for joint crowd counting and individual localization.
Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models
A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial.
Frequency Consistent Adaptation for Real World Super Resolution
From this point of view, we design a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing SR methods to the real scene.
Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation
For intra-domain propagation, we propose an effective self-training strategy to mitigate the noises in pseudo-labeled target domain data and improve the feature discriminability in the target domain.
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection
In this paper, we propose a unified WSOD framework, termed UWSOD, to develop a high-capacity general detection model with only image-level labels, which is self-contained and does not require external modules or additional supervision.
Fast Class-wise Updating for Online Hashing
To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.
Adversarial Refinement Network for Human Motion Prediction
Specifically, we take both the historical motion sequences and coarse prediction as input of our cascaded refinement network to predict refined human motion and strengthen the refinement network with adversarial error augmentation.
Rotated Binary Neural Network
In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version.
Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes.
Face Anti-Spoofing Via Disentangled Representation Learning
Face anti-spoofing is crucial to security of face recognition systems.
Adversarial Semantic Data Augmentation for Human Pose Estimation
Human pose estimation is the task of localizing body keypoints from still images.
Dense Scene Multiple Object Tracking with Box-Plane Matching
Multiple Object Tracking (MOT) is an important task in computer vision.
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking
Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution.
NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination
Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will potentially lead to a lower recall rate and a higher threshold introduces more false positives.
Ranked #7 on
Object Detection
on CrowdHuman (full body)
Temporal Distinct Representation Learning for Action Recognition
Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos.
Collaborative Learning for Faster StyleGAN Embedding
The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator.
ACFD: Asymmetric Cartoon Face Detector
Cartoon face detection is a more challenging task than human face detection due to many difficult scenarios is involved.
Real-World Super-Resolution via Kernel Estimation and Noise Injection
Recent state-of-the-art super-resolution methods have achieved impressive performance on ideal datasets regardless of blur and noise.
Arbitrary Style Transfer via Multi-Adaptation Network
Arbitrary style transfer is a significant topic with research value and application prospect.
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability.
Ranked #13 on
Face Verification
on IJB-C
(TAR @ FAR=1e-4 metric)
Towards Palmprint Verification On Smartphones
First, to facilitate the study of palmprint verification on smartphones, we established an annotated palmprint dataset named MPD, which was collected by multi-brand smartphones in two separate sessions with various backgrounds and illumination conditions.
Architecture Disentanglement for Deep Neural Networks
Based on the experimental results, we present three new findings that provide fresh insights into the inner logic of DNNs.
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015 unsupervised
(Fl-all metric)
ASFD: Automatic and Scalable Face Detector
In this paper, we propose a novel Automatic and Scalable Face Detector (ASFD), which is based on a combination of neural architecture search techniques as well as a new loss design.
Improving Face Recognition from Hard Samples via Distribution Distillation Loss
To improve the performance on those hard samples for general tasks, we propose a novel Distribution Distillation Loss to narrow the performance gap between easy and hard samples, which is a simple, effective and generic for various types of facial variations.
Learning Semantic Neural Tree for Human Parsing
In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results.
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)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
This procedure encourages that the selected training samples can be both clean and miscellaneous, and that the two models can promote each other iteratively.
Ranked #8 on
Unsupervised Domain Adaptation
on Market to Duke
Variational Structured Semantic Inference for Diverse Image Captioning
To model these two inherent diversities in image captioning, we propose a Variational Structured Semantic Inferring model (termed VSSI-cap) executed in a novel structured encoder-inferer-decoder schema.
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.
Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning
In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective.
TEINet: Towards an Efficient Architecture for Video Recognition
To relieve this problem, we propose an efficient temporal module, termed as Temporal Enhancement-and-Interaction (TEI Module), which could be plugged into the existing 2D CNNs (denoted by TEINet).
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.
Semantic-aware Image Deblurring
Specially, we propose a novel Structured-Spatial Semantic Embedding model for image deblurring (termed S3E-Deblur), which introduces a novel Structured-Spatial Semantic tree model (S3-tree) to bridge two basic tasks in computer vision: image deblurring (ImD) and image captioning (ImC).
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Specifically, we incorporate convolutional operations along edges of the tree structure, and use the routing functions in each node to determine the root-to-leaf computational paths within the tree.
Ranked #31 on
Fine-Grained Image Classification
on Stanford Cars
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Semi-Supervised Adversarial Monocular Depth Estimation
In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available.
Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently
Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i. e., feature extraction, region proposal, bounding box regression, and additional layers for rotated region detection.
Interpretable Neural Network Decoupling
More specifically, we introduce a novel architecture controlling module in each layer to encode the network architecture by a vector.
Supervised Online Hashing via Similarity Distribution Learning
In this paper, we propose to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space.
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
The TargetNet module is a neural network for solving a specific task and the MetaNet module aims at learning to generate functional weights for TargetNet by observing training samples.
Anti-Confusing: Region-Aware Network for Human Pose Estimation
In this work, we propose a novel framework named Region-Aware Network (RANet), which learns the ability of anti-confusing in case of heavy occlusion, nearby person and symmetric appearance, for human pose estimation.
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner.
Aurora Guard: Real-Time Face Anti-Spoofing via Light Reflection
In this paper, we propose a light reflection based face anti-spoofing method named Aurora Guard (AG), which is fast, simple yet effective that has already been deployed in real-world systems serving for millions of users.
Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.
Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos
In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation.
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other.
Ranked #2 on
Person Re-Identification
on CUHK03-C
DSFD: Dual Shot Face Detector
In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively.
Ranked #1 on
Face Detection
on FDDB
Attention-based Multi-Patch Aggregation for Image Aesthetic Assessment
Aggregation structures with explicit information, such as image attributes and scene semantics, are effective and popular for intelligent systems for assessing aesthetics of visual data.
Ranked #1 on
Aesthetics Quality Assessment
on AVA
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.
Cross-Modality Binary Code Learning via Fusion Similarity Hashing
In this paper, we propose a hashing scheme, termed Fusion Similarity Hashing (FSH), which explicitly embeds the graph-based fusion similarity across modalities into a common Hamming space.
Fast and Accurate Neural Word Segmentation for Chinese
Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation.
Ordinal Constrained Binary Code Learning for Nearest Neighbor Search
By given a large-scale training data set, it is very expensive to embed such ranking tuples in binary code learning.
Automatic Script Identification in the Wild
With the rapid increase of transnational communication and cooperation, people frequently encounter multilingual scenarios in various situations.
