Search Results for author:
Found 42 papers, 19 papers with code
A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals
One of the biggest challenges to this task is the one-to-many mapping from sparse observations to dense full-body motions, which endowed inherent ambiguities.
HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment
Humans naturally interact with both others and the surrounding multiple objects, engaging in various social activities.
Gaze-guided Hand-Object Interaction Synthesis: Benchmark and Method
Here, the object motion diffusion model generates sequences of object motions based on gaze conditions, while the hand motion diffusion model produces hand motions based on the generated object motion.
THOR: Text to Human-Object Interaction Diffusion via Relation Intervention
This paper addresses new methodologies to deal with the challenging task of generating dynamic Human-Object Interactions from textual descriptions (Text2HOI).
Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
Specifically, for each client, we learn a global prompt to extract consensus knowledge among clients, and a local prompt to capture client-specific category characteristics.
Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport
This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework.
LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment
For human-centric large-scale scenes, fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications.
Guidance with Spherical Gaussian Constraint for Conditional Diffusion
We theoretically show the existence of manifold deviation by establishing a certain lower bound for the estimation error of the loss guidance.
IMUSIC: IMU-based Facial Expression Capture
In this paper, we propose IMUSIC to fill the gap, a novel path for facial expression capture using purely IMU signals, significantly distant from previous visual solutions. The key design in our IMUSIC is a trilogy.
HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations
Existing gait recognition benchmarks mostly include minor clothing variations in the laboratory environments, but lack persistent changes in appearance over time and space.
Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning
Specifically, the online model learns general knowledge that is shared among all clients, while the offline model is trained locally to learn the specialized knowledge of each individual client.
BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics
We further provide a strong baseline method, BOTH2Hands, for the novel task: generating vivid two-hand motions from both implicit body dynamics and explicit text prompts.
Contextually Affinitive Neighborhood Refinery for Deep Clustering
Previous endeavors in self-supervised learning have enlightened the research of deep clustering from an instance discrimination perspective.
CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels
However, the current approaches rely heavily on the model's predictions and evaluate each sample independently without considering either the global and local structure of the sample distribution.
I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions
In this paper, we present I'm-HOI, a monocular scheme to faithfully capture the 3D motions of both the human and object in a novel setting: using a minimal amount of RGB camera and object-mounted Inertial Measurement Unit (IMU).
HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models
We further present a strong baseline method HandDiffuse for the controllable motion generation of interacting hands using various controllers.
Reduced Policy Optimization for Continuous Control with Hard Constraints
To the best of our knowledge, RPO is the first attempt that introduces GRG to RL as a way of efficiently handling both equality and inequality hard constraints.
Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation
Deep Equilibrium Models (DEQs) and Neural Ordinary Differential Equations (Neural ODEs) are two branches of implicit models that have achieved remarkable success owing to their superior performance and low memory consumption.
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
This paper presents an inverse kinematic optimization layer (IKOL) for 3D human pose and shape estimation that leverages the strength of both optimization- and regression-based methods within an end-to-end framework.
Ranked #24 on
3D Human Pose Estimation
on 3DPW
Robust Knowledge Adaptation for Federated Unsupervised Person ReID
Thus, in this work, a federated unsupervised cluster-contrastive (FedUCC) learning method is proposed for Person ReID.
NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
We construct a dense multi-view dome to acquire a complex human object interaction dataset, named HODome, that consists of $\sim$75M frames on 10 subjects interacting with 23 objects.
Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR
Motivated by this, we propose a monocular camera and single LiDAR-based method for 3D multi-person pose estimation in large-scale scenes, which is easy to deploy and insensitive to light.
Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation
Lifelong person re-identification (LReID) is in significant demand for real-world development as a large amount of ReID data is captured from diverse locations over time and cannot be accessed at once inherently.
Responsible Active Learning via Human-in-the-loop Peer Study
To further enhance the active learner via large-scale unlabelled data, we introduce multiple peer students into the active learner which is trained by a novel learning paradigm, including the In-Class Peer Study on labelled data and the Out-of-Class Peer Study on unlabelled data.
Knowledge-Aware Federated Active Learning with Non-IID Data
In this paper, we propose a federated active learning paradigm to efficiently learn a global model with limited annotation budget while protecting data privacy in a decentralized learning way.
LiCamGait: Gait Recognition in the Wild by Using LiDAR and Camera Multi-modal Visual Sensors
LiDAR can capture accurate depth information in large-scale scenarios without the effect of light conditions, and the captured point cloud contains gait-related 3D geometric properties and dynamic motion characteristics.
FedTP: Federated Learning by Transformer Personalization
Instead of using a vanilla personalization mechanism that maintains personalized self-attention layers of each client locally, we develop a learn-to-personalize mechanism to further encourage the cooperation among clients and to increase the scablability and generalization of FedTP.
Unified Optimal Transport Framework for Universal Domain Adaptation
Notably, UniOT is the first method with the capability to automatically discover and recognize private categories in the target domain for UniDA.
Ranked #3 on
Universal Domain Adaptation
on Office-Home
Alternating Differentiation for Optimization Layers
In this paper, we developed a new framework, named Alternating Differentiation (Alt-Diff), that differentiates optimization problems (here, specifically in the form of convex optimization problems with polyhedral constraints) in a fast and recursive way.
SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parametric Generator
Named after the fossils of one of the oldest known human ancestors, our LUCY dataset contains high-quality Computed Tomography (CT) scans of the complete human head before and after orthognathic surgeries, critical for evaluating surgery results.
Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
This method first uses 2. 5D pose and geometry information to infer camera-centric root depths in a forward pass, and then exploits the root depths to further improve representation learning of 2. 5D pose estimation in a backward pass.
HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions
Monocular 3D motion capture (mocap) is beneficial to many applications.
Ranked #1 on
Pose Estimation
on 3DPW
OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification
Transformers have shown preferable performance on many vision tasks.
Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions
In this paper, we propose a neural human performance capture and rendering system to generate both high-quality geometry and photo-realistic texture of both human and objects under challenging interaction scenarios in arbitrary novel views, from only sparse RGB streams.
Embedding-based Recommender System for Job to Candidate Matching on Scale
The overall improvement of our job to candidate matching system has demonstrated its feasibility and scalability at a major online recruitment site.
Online Multiple Object Tracking with Cross-Task Synergy
On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts.
Symbiotic Adversarial Learning for Attribute-based Person Search
The current state-of-the-art methods either focus on learning better cross-modal embeddings by mining only seen data, or they explicitly use generative adversarial networks (GANs) to synthesize unseen features.
Pose-guided Visible Part Matching for Occluded Person ReID
Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario.
Tripartite Vector Representations for Better Job Recommendation
Job recommendation is a crucial part of the online job recruitment business.
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair.
Ranked #22 on
Unsupervised Domain Adaptation
on Market to Duke
Attribute Recognition by Joint Recurrent Learning of Context and Correlation
Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small.
Discovering Visual Concept Structure with Sparse and Incomplete Tags
As a result, our model is able to discover more accurate semantic correlation between textual tags and visual features, and finally providing favourable visual semantics interpretation even with highly sparse and incomplete tags.
