Search Results for author: Zhiyu Cheng

Found 4 papers, 2 papers with code

SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos

no code implementations14 Apr 2022 Anthony Cioppa, Silvio Giancola, Adrien Deliege, Le Kang, Xin Zhou, Zhiyu Cheng, Bernard Ghanem, Marc Van Droogenbroeck

Tracking objects in soccer videos is extremely important to gather both player and team statistics, whether it is to estimate the total distance run, the ball possession or the team formation.

Multiple Object Tracking

ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization

1 code implementation29 Mar 2022 Bo He, Xitong Yang, Le Kang, Zhiyu Cheng, Xin Zhou, Abhinav Shrivastava

Without the boundary information of action segments, existing methods mostly rely on multiple instance learning (MIL), where the predictions of unlabeled instances (i. e., video snippets) are supervised by classifying labeled bags (i. e., untrimmed videos).

14 Weakly Supervised Temporal Action Localization

Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection

1 code implementation28 Jun 2021 Xin Zhou, Le Kang, Zhiyu Cheng, Bo He, Jingyu Xin

With rapidly evolving internet technologies and emerging tools, sports related videos generated online are increasing at an unprecedentedly fast pace.

Action Recognition Action Spotting +2

CURSOR-BASED ADAPTIVE QUANTIZATION FOR DEEP NEURAL NETWORK

no code implementations25 Sep 2019 Bapu Li(*), Yanwen Fan(*), Zhiyu Cheng, Yingze Bao (* means equal contribution)

We further devise a new loss function in the search process to simultaneously optimize accuracy and parameter size of the model.

Quantization

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