Search Results for author: Taojiannan Yang

Found 22 papers, 16 papers with code

A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition

1 code implementation ICCV 2023 Andong Deng, Taojiannan Yang, Chen Chen

The goal of building a benchmark (suite of datasets) is to provide a unified protocol for fair evaluation and thus facilitate the evolution of a specific area.

Action Recognition Representation Learning +3

AIM: Adapting Image Models for Efficient Video Action Recognition

1 code implementation6 Feb 2023 Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, Mu Li

Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks.

 Ranked #1 on Action Recognition on Diving-48 (using extra training data)

Action Classification Action Recognition +2

Language-Assisted Deep Learning for Autistic Behaviors Recognition

no code implementations17 Nov 2022 Andong Deng, Taojiannan Yang, Chen Chen, Qian Chen, Leslie Neely, Sakiko Oyama

In such cases, automatic recognition systems based on computer vision and machine learning (in particular deep learning) technology can alleviate this issue to a large extent.

Action Recognition Multimodal Deep Learning +1

Revisiting Training-free NAS Metrics: An Efficient Training-based Method

1 code implementation16 Nov 2022 Taojiannan Yang, Linjie Yang, Xiaojie Jin, Chen Chen

In this paper, we revisit these training-free metrics and find that: (1) the number of parameters (\#Param), which is the most straightforward training-free metric, is overlooked in previous works but is surprisingly effective, (2) recent training-free metrics largely rely on the \#Param information to rank networks.

Neural Architecture Search

Conquering the Communication Constraints to Enable Large Pre-Trained Models in Federated Learning

no code implementations4 Oct 2022 Guangyu Sun, Matias Mendieta, Taojiannan Yang, Chen Chen

Recently, the use of small pre-trained models has been shown effective in federated learning optimization and improving convergence.

Federated Learning

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

1 code implementation CVPR 2023 Ce Zheng, Matias Mendieta, Taojiannan Yang, Guo-Jun Qi, Chen Chen

Recently, vision transformers have shown great success in a set of human reconstruction tasks such as 2D human pose estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh reconstruction (HMR) tasks.

2D Human Pose Estimation 3D Human Pose Estimation

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

1 code implementation CVPR 2022 Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen

To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.

Federated Learning Privacy Preserving

MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations

1 code implementation14 May 2021 Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen

MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.

Action Recognition Image Classification +2

3D Human Pose Estimation with Spatial and Temporal Transformers

3 code implementations ICCV 2021 Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation.

Image Classification Monocular 3D Human Pose Estimation +3

Consistency-based Active Learning for Object Detection

1 code implementation18 Mar 2021 Weiping Yu, Sijie Zhu, Taojiannan Yang, Chen Chen

Unlike most recent works that focused on applying active learning for image classification, we propose an effective Consistency-based Active Learning method for object Detection (CALD), which fully explores the consistency between original and augmented data.

Active Learning Classification +5

VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval

1 code implementation CVPR 2021 Sijie Zhu, Taojiannan Yang, Chen Chen

In this paper, we redefine this problem with a more realistic assumption that the query image can be arbitrary in the area of interest and the reference images are captured before the queries emerge.

Image-Based Localization Image Retrieval

A3D: Adaptive 3D Networks for Video Action Recognition

no code implementations24 Nov 2020 Sijie Zhu, Taojiannan Yang, Matias Mendieta, Chen Chen

Even under the same computational constraints, the performance of our adaptive networks can be significantly boosted over the baseline counterparts by the mutual training along three dimensions.

Action Recognition Temporal Action Localization

Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection

1 code implementation7 Nov 2020 Weiping Yu, Taojiannan Yang, Chen Chen

To this end, we rethink long-tailed object detection in UAV images and propose the Dual Sampler and Head detection Network (DSHNet), which is the first work that aims to resolve long-tail distribution in UAV images.

Head Detection Image Cropping +2

GradAug: A New Regularization Method for Deep Neural Networks

1 code implementation NeurIPS 2020 Taojiannan Yang, Sijie Zhu, Chen Chen

The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process.

Instance Segmentation object-detection +2

Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation

no code implementations23 May 2020 Sijie Zhu, Taojiannan Yang, Chen Chen

Street-to-aerial image geo-localization, which matches a query street-view image to the GPS-tagged aerial images in a reference set, has attracted increasing attention recently.

Metric Learning

Density Map Guided Object Detection in Aerial Images

1 code implementation12 Apr 2020 Changlin Li, Taojiannan Yang, Sijie Zhu, Chen Chen, Shanyue Guan

Specifically, we propose a Density-Map guided object detection Network (DMNet), which is inspired from the observation that the object density map of an image presents how objects distribute in terms of the pixel intensity of the map.

Image Cropping Object +3

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

2 code implementations ECCV 2020 Taojiannan Yang, Sijie Zhu, Chen Chen, Shen Yan, Mi Zhang, Andrew Willis

We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime.

Instance Segmentation object-detection +3

Visual Explanation for Deep Metric Learning

1 code implementation27 Sep 2019 Sijie Zhu, Taojiannan Yang, Chen Chen

This work explores the visual explanation for deep metric learning and its applications.

Metric Learning Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.