Search Results for author: Xuan Yang

Found 17 papers, 7 papers with code

PolyMaX: General Dense Prediction with Mask Transformer

1 code implementation9 Nov 2023 Xuan Yang, Liangzhe Yuan, Kimberly Wilber, Astuti Sharma, Xiuye Gu, Siyuan Qiao, Stephanie Debats, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko, Liang-Chieh Chen

Despite this shift, methods based on the per-pixel prediction paradigm still dominate the benchmarks on the other dense prediction tasks that require continuous outputs, such as depth estimation and surface normal prediction.

Monocular Depth Estimation Semantic Segmentation +2

VideoGLUE: Video General Understanding Evaluation of Foundation Models

1 code implementation6 Jul 2023 Liangzhe Yuan, Nitesh Bharadwaj Gundavarapu, Long Zhao, Hao Zhou, Yin Cui, Lu Jiang, Xuan Yang, Menglin Jia, Tobias Weyand, Luke Friedman, Mikhail Sirotenko, Huisheng Wang, Florian Schroff, Hartwig Adam, Ming-Hsuan Yang, Ting Liu, Boqing Gong

We evaluate existing foundation models video understanding capabilities using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition, temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring a foundation model (FM) for a downstream task.

Action Recognition Temporal Localization +1

Spatial-temporal traffic modeling with a fusion graph reconstructed by tensor decomposition

no code implementations12 Dec 2022 Qin Li, Xuan Yang, Yong Wang, Yuankai Wu, Deqiang He

This paper proposes reconstructing the binary adjacency matrix via tensor decomposition, and a traffic flow forecasting method is proposed.

Open-Ended Question Answering Tensor Decomposition

MMGA: Multimodal Learning with Graph Alignment

no code implementations18 Oct 2022 Xuan Yang, Quanjin Tao, Xiao Feng, Donghong Cai, Xiang Ren, Yang Yang

In this paper, we propose MMGA (Multimodal learning with Graph Alignment), a novel multimodal pre-training framework to incorporate information from graph (social network), image and text modalities on social media to enhance user representation learning.

Representation Learning

On Label Granularity and Object Localization

1 code implementation20 Jul 2022 Elijah Cole, Kimberly Wilber, Grant van Horn, Xuan Yang, Marco Fornoni, Pietro Perona, Serge Belongie, Andrew Howard, Oisin Mac Aodha

Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels.

Object Weakly-Supervised Object Localization

DropMessage: Unifying Random Dropping for Graph Neural Networks

2 code implementations21 Apr 2022 Taoran Fang, Zhiqing Xiao, Chunping Wang, Jiarong Xu, Xuan Yang, Yang Yang

First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models.

Graph Representation Learning

Coverage Control Algorithm for DSNs Based on Improved Gravitational Search

no code implementations IEEE Sensors Journal 2022 Yindi Yao, Huanmin Liao, Xiong Li, Student Member, IEEE, Feng Zhao, Xuan Yang, and Shanshan Hu

—In directional sensor networks (DSNs), coverage control is an important way to ensure efficient communication and reliable data transmission.


When Does Contrastive Visual Representation Learning Work?

no code implementations CVPR 2022 Elijah Cole, Xuan Yang, Kimberly Wilber, Oisin Mac Aodha, Serge Belongie

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification.

Contrastive Learning Fine-Grained Image Classification +2

A Fast and Precise Method for Large-Scale Land-Use Mapping Based on Deep Learning

no code implementations9 Aug 2019 Xuan Yang, Zhengchao Chen, Baipeng Li, Dailiang Peng, Pan Chen, Bing Zhang

The land-use map is an important data that can reflect the use and transformation of human land, and can provide valuable reference for land-use planning.

Classification General Classification +1

DNN Dataflow Choice Is Overrated

no code implementations10 Sep 2018 Xuan Yang, Mingyu Gao, Jing Pu, Ankita Nayak, Qiaoyi Liu, Steven Emberton Bell, Jeff Ou Setter, Kaidi Cao, Heonjae Ha, Christos Kozyrakis, Mark Horowitz

Many DNN accelerators have been proposed and built using different microarchitectures and program mappings.

Distributed, Parallel, and Cluster Computing

Programming Heterogeneous Systems from an Image Processing DSL

3 code implementations28 Oct 2016 Jing Pu, Steven Bell, Xuan Yang, Jeff Setter, Stephen Richardson, Jonathan Ragan-Kelley, Mark Horowitz

We address this problem by extending the image processing language, Halide, so users can specify which portions of their applications should become hardware accelerators, and then we provide a compiler that uses this code to automatically create the accelerator along with the "glue" code needed for the user's application to access this hardware.

Software Engineering

A Systematic Approach to Blocking Convolutional Neural Networks

1 code implementation14 Jun 2016 Xuan Yang, Jing Pu, Blaine Burton Rister, Nikhil Bhagdikar, Stephen Richardson, Shahar Kvatinsky, Jonathan Ragan-Kelley, Ardavan Pedram, Mark Horowitz

Convolutional Neural Networks (CNNs) are the state of the art solution for many computer vision problems, and many researchers have explored optimized implementations.


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