Search Results for author:
Found 93 papers, 51 papers with code
Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos
Temporal information can provide additional cues about the location of body joints and help to alleviate these issues.
Ranked #4 on
Pose Estimation
on UPenn Action
Learning Human Motion Models for Long-term Predictions
Furthermore, we propose new evaluation protocols to assess the quality of synthetic motion sequences even for which no ground truth data exists.
Cross-modal Deep Variational Hand Pose Estimation
Furthermore, we show that our proposed method can be used without changes on depth images and performs comparably to specialized methods.
Transductive Unbiased Embedding for Zero-Shot Learning
Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes.
Selective Zero-Shot Classification with Augmented Attributes
We propose a selective zero-shot classifier based on both the human defined and the automatically discovered residual attributes.
Amalgamating Knowledge towards Comprehensive Classification
We propose in this paper to study a new model-reusing task, which we term as \emph{knowledge amalgamation}.
End-to-end Learning for Graph Decomposition
The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials.
Monocular Neural Image Based Rendering with Continuous View Control
The approach is self-supervised and only requires 2D images and associated view transforms for training.
Unpaired Pose Guided Human Image Generation
This paper studies the task of full generative modelling of realistic images of humans, guided only by coarse sketch of the pose, while providing control over the specific instance or type of outfit worn by the user.
Investigation of wind pressures on tall building under interference effects using machine learning techniques
This study used machine learning techniques to resolve the conflicting requirement between limited wind tunnel tests that produce unreliable results and a completed investigation of the interference effects that is costly and time-consuming.
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
To this end, we introduce a dual-step strategy that first extracts the task-specific knowledge from the heterogeneous teachers sharing the same sub-task, and then amalgamates the extracted knowledge to build the student network.
Deep Model Transferability from Attribution Maps
Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter.
Data-Free Adversarial Distillation
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer.
DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
In this paper, we propose the DEeP Attribution gRAph (DEPARA) to investigate the transferability of knowledge learned from PR-DNNs.
Impression Space from Deep Template Network
This network is referred to as the {\emph{Template Network}} because its filters will be used as templates to reconstruct images from the impression.
Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images
In this way, rich image appearance models together with more contextual information are integrated by learning a series of decision tree ensembles.
Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances.
Human Body Model Fitting by Learned Gradient Descent
We propose a novel algorithm for the fitting of 3D human shape to images.
Ranked #9 on
3D Human Pose Estimation
on EMDB
Convolutional Autoencoders for Human Motion Infilling
At the heart of our approach lies the idea to cast motion infilling as an inpainting problem and to train a convolutional de-noising autoencoder on image-like representations of motion sequences.
Progressive Network Grafting for Few-Shot Knowledge Distillation
In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category.
Self-Born Wiring for Neural Trees
Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter.
EM-POSE: 3D Human Pose Estimation From Sparse Electromagnetic Trackers
To this end, we present a method to estimate SMPL parameters from 6-12 EM sensors.
Training Generative Adversarial Networks in One Stage
Based on the adversarial losses of the generator and discriminator, we categorize GANs into two classes, Symmetric GANs and Asymmetric GANs, and introduce a novel gradient decomposition method to unify the two, allowing us to train both classes in one stage and hence alleviate the training effort.
Data-Driven Short-Term Voltage Stability Assessment Based on Spatial-Temporal Graph Convolutional Network
The proposed STGCN utilizes graph convolution to integrate network topology information into the learning model to exploit spatial information.
DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network
In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL.
Auto-Validate: Unsupervised Data Validation Using Data-Domain Patterns Inferred from Data Lakes
Complex data pipelines are increasingly common in diverse applications such as BI reporting and ML modeling.
KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation
Knowledge distillation (KD) has recently emerged as an efficacious scheme for learning compact deep neural networks (DNNs).
Contrastive Model Inversion for Data-Free Knowledge Distillation
In this paper, we propose Contrastive Model Inversion~(CMI), where the data diversity is explicitly modeled as an optimizable objective, to alleviate the mode collapse issue.
Tree-Like Decision Distillation
Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.
Distribution Knowledge Embedding for Graph Pooling
A DKEPool network de facto disassembles representation learning into two stages, structure learning and distribution learning.
Shape-aware Multi-Person Pose Estimation from Multi-View Images
In this paper we contribute a simple yet effective approach for estimating 3D poses of multiple people from multi-view images.
Ranked #16 on
3D Multi-Person Pose Estimation
on Shelf
3D Multi-Person Pose Estimation
Multi-Person Pose Estimation
Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
Knowledge distillation~(KD) aims to craft a compact student model that imitates the behavior of a pre-trained teacher in a target domain.
Render In-between: Motion Guided Video Synthesis for Action Interpolation
We propose to address these issues in a motion-guided frame-upsampling framework that is capable of producing realistic human motion and appearance.
Human Performance Capture from Monocular Video in the Wild
In this work, we propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input.
D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose.
Safe Distillation Box
In other words, all users may employ a model in SDB for inference, but only authorized users get access to KD from the model.
A Survey of Deep Learning for Low-Shot Object Detection
Although few-shot learning and zero-shot learning have been extensively explored in the field of image classification, it is indispensable to design new methods for object detection in the data-scarce scenario since object detection has an additional challenging localization task.
Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training
Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV).
Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
The aggregate gradient strategy is a versatile module for mainstream CNN classifiers.
Auto-Tag: Tagging-Data-By-Example in Data Lakes
As data lakes become increasingly popular in large enterprises today, there is a growing need to tag or classify data assets (e. g., files and databases) in data lakes with additional metadata (e. g., semantic column-types), as the inferred metadata can enable a range of downstream applications like data governance (e. g., GDPR compliance), and dataset search.
Up to 100$\times$ Faster Data-free Knowledge Distillation
At the heart of our approach is a novel strategy to reuse the shared common features in training data so as to synthesize different data instances.
gDNA: Towards Generative Detailed Neural Avatars
Furthermore, we show that our method can be used on the task of fitting human models to raw scans, outperforming the previous state-of-the-art.
Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN
The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction.
PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence
We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence.
Knowledge Amalgamation for Object Detection with Transformers
Moreover, the transformer-based students excel in learning amalgamated knowledge, as they have mastered heterogeneous detection tasks rapidly and achieved superior or at least comparable performance to those of the teachers in their specializations.
Meta-attention for ViT-backed Continual Learning
Continual learning is a longstanding research topic due to its crucial role in tackling continually arriving tasks.
Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction
Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis.
An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers
in the heterogeneous graph of scientific papers.
Mining and searching association relation of scientific papers based on deep learning
There is a complex correlation among the data of scientific papers.
Spot-adaptive Knowledge Distillation
Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks.
Distribution-Aware Graph Representation Learning for Transient Stability Assessment of Power System
As the topology of the power system is in the form of graph structure, graph neural network based representation learning is naturally suitable for learning the status of the power system.
Learning Domain Adaptive Object Detection with Probabilistic Teacher
In addition, we conduct anchor adaptation in parallel with localization adaptation, since anchor can be regarded as a learnable parameter.
Slimmable Domain Adaptation
In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs.
Label Matching Semi-Supervised Object Detection
To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.
Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework
Despite the promising results achieved, state-of-the-art interactive reinforcement learning schemes rely on passively receiving supervision signals from advisor experts, in the form of either continuous monitoring or pre-defined rules, which inevitably result in a cumbersome and expensive learning process.
Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning
In this work, we introduce a novel interactiOn Pattern disenTangling (OPT) method, to disentangle not only the joint value function into agent-wise value functions for decentralized execution, but also the entity interactions into interaction prototypes, each of which represents an underlying interaction pattern within a subgroup of the entities.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Learning with Recoverable Forgetting
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge.
Federated Selective Aggregation for Knowledge Amalgamation
The goal of FedSA is to train a student model for a new task with the help of several decentralized teachers, whose pre-training tasks and data are different and agnostic.
ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition
The global prototypes are adopted to provide the global view of objects to guide local prototypes to concentrate on the foreground while eliminating the influence of the background.
A Survey of Neural Trees
This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability.
Attention Diversification for Domain Generalization
Under this guidance, a novel Attention Diversification framework is proposed, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated to reassign appropriate attention to diverse task-related features.
A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges
In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods.
Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition
Value Decomposition (VD) aims to deduce the contributions of agents for decentralized policies in the presence of only global rewards, and has recently emerged as a powerful credit assignment paradigm for tackling cooperative Multi-Agent Reinforcement Learning (MARL) problems.
Fast-SNARF: A Fast Deformer for Articulated Neural Fields
A key challenge in making such methods applicable to articulated objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space.
Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks
Part-prototype networks (e. g., ProtoPNet, ProtoTree, and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts.
An Effective Methodology for Short-Circuit Calculation of Power Systems Dominated by Power Electronics Converters Considering Unbalanced Voltage Conditions and Converter Limits
A novel methodology has been presented to identify short-circuit equilibrium point of the studied system considering the operation and limitations of power converters.
InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds
To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty space-skipping strategy for dynamic scenes.
Recent advances in artificial intelligence for retrosynthesis
Afterwards, we analyze these methods in terms of their mechanism and performance, and introduce popular evaluation metrics for them, in which we also provide a detailed comparison among representative methods on several public datasets.
Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition
Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose parameters.
Battery Valuation and Management for Battery Swapping Station with an Intertemporal Framework
Battery swapping as a business model for battery energy storage (BES) has great potential in future integrated low-carbon energy and transportation systems.
X-Avatar: Expressive Human Avatars
Our method models bodies, hands, facial expressions and appearance in a holistic fashion and can be learned from either full 3D scans or RGB-D data.
Schema Inference for Interpretable Image Classification
In this paper, we study a novel inference paradigm, termed as schema inference, that learns to deductively infer the explainable predictions by rebuilding the prior deep neural network (DNN) forwarding scheme, guided by the prevalent philosophical cognitive concept of schema.
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation
Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability.
Hi4D: 4D Instance Segmentation of Close Human Interaction
We propose Hi4D, a method and dataset for the automatic analysis of physically close human-human interaction under prolonged contact.
Human from Blur: Human Pose Tracking from Blurry Images
The key idea is to tackle the inverse problem of image deblurring by modeling the forward problem with a 3D human model, a texture map, and a sequence of poses to describe human motion.
Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation
The whole temporal neighborhood of nodes reveals the varying preferences of nodes.
Learning Locally Editable Virtual Humans
To this end, we construct a trainable feature codebook to store local geometry and texture features on the vertices of a deformable body model, thus exploiting its consistent topology under articulation.
Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
Despite the encouraging results achieved, CTDE makes an independence assumption on agent policies, which limits agents to adopt global cooperative information from each other during centralized training.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
A general Temperature-Guided Language model to engineer enhanced Stability and Activity in Proteins
Designing protein mutants with high stability and activity is a critical yet challenging task in protein engineering.
EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild
EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape parameters with global body and camera trajectories for in-the-wild videos.
ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose.
ModelGiF: Gradient Fields for Model Functional Distance
The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes.
SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition
Moreover, it also achieves SOTA performance across all methods on three datasets, utilizing approximately 0. 3\% of the parameters and 0. 5\% of power consumption employed by artificial neural networks (ANNs).
Zeroth-Order Feedback-Based Optimization for Distributed Demand Response
Distributed demand response is a typical distributed optimization problem that requires coordination among multiple agents to satisfy demand response requirements.
SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers
In this paper, we introduce a framework that can generate plausible human grasping motions suitable for training the robot.
Load Data Valuation in Multi-Energy Systems: An End-to-End Approach
Accurate load forecasting serves as the foundation for the flexible operation of multi-energy systems (MES).
SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion
For the former, we employ a powerful generative diffusion model to hallucinate unseen back-view appearance based on the input images.
Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning
Instead, we employ a proxy model to extract state features that are both discriminative (adaptive to the agent) and generally applicable (robust to agent noise).
Powerformer: A Section-adaptive Transformer for Power Flow Adjustment
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections.
Training-Free Pretrained Model Merging
Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task.
Pre-Trained Model Recommendation for Downstream Fine-tuning
As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task.
On the Concept Trustworthiness in Concept Bottleneck Models
Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention due to their remarkable interpretability achieved by the interpretable concept bottleneck.
GraspXL: Generating Grasping Motions for Diverse Objects at Scale
Moreover, we show that our framework can be deployed to different dexterous hands and work with reconstructed or generated objects.
