Search Results for author:
Found 26 papers, 11 papers with code
Semantic Prompt for Few-Shot Image Recognition
Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively.
Free Lunch for Domain Adversarial Training: Environment Label Smoothing
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data.
Ranked #2 on
Domain Adaptation
on Office-Home
Human Image Generation: A Comprehensive Survey
Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value.
Domain-Specific Risk Minimization for Out-of-Distribution Generalization
Our bound motivates two strategies to reduce the gap: the first one is ensembling multiple classifiers to enrich the hypothesis space, then we propose effective gap estimation methods for guiding the selection of a better hypothesis for the target.
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.
Completing Networks by Learning Local Connection Patterns
And experiments show that our model perform better on a network with higher Reachable CC.
Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Data
In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data.
Intention Recognition for Multiple Agents
Then, we transform the intention recognition into an un-supervised learning problem and adapt a clustering algorithm to group intentions of multiple agents through comparing their behavioural models.
Generalizable Person Re-identification Without Demographics
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints.
Ranked #9 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Learning Domain Invariant Representations for Generalizable Person Re-Identification
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community.
Focal and Efficient IOU Loss for Accurate Bounding Box Regression
(ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR.
Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition
However, the complexity of the State-Of-The-Art (SOTA) models of this task tends to be exceedingly sophisticated and over-parameterized, where the low efficiency in model training and inference has obstructed the development in the field, especially for large-scale action datasets.
Ranked #16 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition
More crucially, on the synthetic occlusion and jittering datasets, the performance deterioration due to the occluded and disturbed joints can be significantly alleviated by utilizing the proposed RA-GCN.
Ranked #29 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Inference for Network Structure and Dynamics from Time Series Data via Graph Neural Network
We carried out experiments on discrete and continuous time series data.
Slow Feature Analysis for Human Action Recognition
In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts.
Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons
To enhance the robustness of action recognition models to incomplete skeletons, we propose a multi-stream graph convolutional network (GCN) for exploring sufficient discriminative features distributed over all skeleton joints.
Ranked #57 on
Skeleton Based Action Recognition
on NTU RGB+D
Large-Scale Pedestrian Retrieval Competition
The Large-Scale Pedestrian Retrieval Competition (LSPRC) mainly focuses on person retrieval which is an important end application in intelligent vision system of surveillance.
A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.
The Cinderella Complex: Word Embeddings Reveal ender Stereotypes in Movies and Books
Our analysis of thousands of movies and books reveals how these cultural products weave stereotypical gender roles into morality tales and perpetuate gender inequality through storytelling.
Adversarially Occluded Samples for Person Re-Identification
Person re-identification (ReID) is the task of retrieving particular persons across different cameras.
Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a fundamental problem in ReID and is still an open problem today.
Ranked #99 on
Person Re-Identification
on Market-1501
A Large-scale Distributed Video Parsing and Evaluation Platform
Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world.
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes.
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data.
A Richly Annotated Dataset for Pedestrian Attribute Recognition
RAP has in total 41, 585 pedestrian samples, each of which is annotated with 72 attributes as well as viewpoints, occlusions, body parts information.
