Search Results for author:
Found 59 papers, 29 papers with code
ReGenNet: Towards Human Action-Reaction Synthesis
Humans constantly interact with their surrounding environments.
Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks.
Correlation-Embedded Transformer Tracking: A Single-Branch Framework
Thus, we reformulate the two-branch Siamese tracking as a conceptually simple, fully transformer-based Single-Branch Tracking pipeline, dubbed SBT.
Inter-X: Towards Versatile Human-Human Interaction Analysis
We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects.
RLLTE: Long-Term Evolution Project of Reinforcement Learning
We present RLLTE: a long-term evolution, extremely modular, and open-source framework for reinforcement learning (RL) research and application.
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive Survey
Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation.
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC).
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Training offline reinforcement learning (RL) models using visual inputs poses two significant challenges, i. e., the overfitting problem in representation learning and the overestimation bias for expected future rewards.
NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
They are complementary -- the outer navigation is to identify global-view semantic directions, and the inner refinement dedicates to fine-grained attributes.
Inpaint Anything: Segment Anything Meets Image Inpainting
We are also very willing to help everyone share and promote new projects based on our Inpaint Anything (IA).
[CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Based on that, we build upon the CLIP model as a backbone which we extend with a One-Way [CLS] token navigation from text to the visual branch that enables zero-shot dense prediction, dubbed \textbf{ClsCLIP}.
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations.
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning
We present AIRS: Automatic Intrinsic Reward Shaping that intelligently and adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement learning (RL).
Tackling Visual Control via Multi-View Exploration Maximization
We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks.
Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning
Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards.
A Nonparametric Contextual Bandit with Arm-level Eligibility Control for Customer Service Routing
Routing contacts to eligible SMEs turns out to be a non-trivial problem because SMEs' domain eligibility is subject to training quality and can change over time.
Robust Multi-Object Tracking by Marginal Inference
To address the problem, we present an efficient approach to compute a marginal probability for each pair of objects in real time.
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked.
3D Multi-Person Pose Estimation (absolute)
3D Pose Estimation
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
Most of existing methods for this task rely heavily on convolutional neural networks, which however have trouble capturing long-range dependencies between entities in the language expression and are not flexible enough for modeling interactions between the two different modalities.
Ranked #12 on
Referring Expression Segmentation
on RefCoCo val
ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation
We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions.
Correlation-Aware Deep Tracking
In contrast to the Siamese-like feature extraction, our network deeply embeds cross-image feature correlation in multiple layers of the feature network.
Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph
Last, an innovative link attention module serves as the decoder to reconstruct data from the decomposed content and style, with the help of the linking keys.
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism
It can be even replaced by a zero-parameter operation.
Ranked #67 on
Object Detection
on COCO minival
(APM metric)
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation
In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID.
Domain Adaptive Person Re-Identification
Knowledge Distillation
+4
SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation
Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks.
Learning Tracking Representations via Dual-Branch Fully Transformer Networks
We present a Siamese-like Dual-branch network based on solely Transformers for tracking.
Confounder Identification-free Causal Visual Feature Learning
In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders.
Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition
Skeleton data carries valuable motion information and is widely explored in human action recognition.
WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation
We also present a method which injects styles of the web-crawled images into training images on-the-fly during training, which enables the network to experience images of diverse styles with reliable labels for effective training.
Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript.
Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?
Specifically, we replace the MLP module in the token-mixing step with a novel sparse MLP (sMLP) module.
Ranked #391 on
Image Classification
on ImageNet
A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision.
Self-Supervised Visual Representations Learning by Contrastive Mask Prediction
In this paper, we propose a novel contrastive mask prediction (CMP) task for visual representation learning and design a mask contrast (MaskCo) framework to implement the idea.
VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild
We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint.
Ranked #7 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
Occluded person re-identification (ReID) aims to match person images with occlusion.
Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow
For marketing, we sometimes need to recommend content for multiple pages in sequence.
ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation
Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain.
PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning.
Continuous Control (100k environment steps)
Continuous Control (500k environment steps)
+3
Understanding Mobile GUI: from Pixel-Words to Screen-Sentences
A dataset, RICO-PW, of screenshots with Pixel-Words annotations is built based on the public RICO dataset, which will be released to help to address the lack of high-quality training data in this area.
Unsupervised Visual Representation Learning by Tracking Patches in Video
The proxy task is to estimate the position and size of the image patch in a sequence of video frames, given only the target bounding box in the first frame.
S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation
S2R-DepthNet consists of: a) a Structure Extraction (STE) module which extracts a domaininvariant structural representation from an image by disentangling the image into domain-invariant structure and domain-specific style components, b) a Depth-specific Attention (DSA) module, which learns task-specific knowledge to suppress depth-irrelevant structures for better depth estimation and generalization, and c) a depth prediction module (DP) to predict depth from the depth-specific representation.
Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation.
MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics.
Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation
Many unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap, where a feature extractor is trained to fool a domain discriminator in order to have aligned feature distributions.
Generalizing to Unseen Domains: A Survey on Domain Generalization
Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.
Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias.
Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View
Based on this observation, we argue that it is possible to mitigate the trade-off by $(i)$ leveraging the pretrained generative models with high generation quality, $(ii)$ focusing on discovering the traversal directions as factors for disentangled representation learning.
Towards Building A Group-based Unsupervised Representation Disentanglement Framework
We then propose a model, based on existing VAE-based methods, to tackle the unsupervised learning problem of the framework.
AttributeNet: Attribute Enhanced Vehicle Re-Identification
Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints.
Ranked #1 on
Vehicle Re-Identification
on VeRi-Wild Large
General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework
This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning.
VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wild
We believe that VAE$^2$ is also applicable to other stochastic sequence prediction problems where training data are lack of stochasticity.
Style Normalization and Restitution for Domain Generalization and Adaptation
In this paper, we design a novel Style Normalization and Restitution module (SNR) to simultaneously ensure both high generalization and discrimination capability of the networks.
Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the identity (ID) classification loss per sample, the triplet loss, and the contrastive loss.
An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation
The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for images under different augmentations.
Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
In essence, current re-ID overemphasizes the importance of retrieval but underemphasizes that of verification, \textit{i. e.}, all returned images are considered as the target.
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views.
Ranked #1 on
3D Human Pose Estimation
on Total Capture
Uncertainty-Aware Few-Shot Image Classification
In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization.
FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Optical Flow Estimation
To exploit such flexible and comprehensive information, we propose a semi-supervised Feature Pyramidal Correlation and Residual Reconstruction Network (FPCR-Net) for optical flow estimation from frame pairs.
