Search Results for author: Bo He

Found 11 papers, 3 papers with code

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).

Weakly Supervised Temporal Action Localization

NeRV: Neural Representations for Videos

1 code implementation NeurIPS 2021 Hao Chen, Bo He, Hanyu Wang, Yixuan Ren, Ser-Nam Lim, Abhinav Shrivastava

In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H. 264, HEVC \etc).

Denoising Frame +3

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

GTA: Global Temporal Attention for Video Action Understanding

no code implementations15 Dec 2020 Bo He, Xitong Yang, Zuxuan Wu, Hao Chen, Ser-Nam Lim, Abhinav Shrivastava

To this end, we introduce Global Temporal Attention (GTA), which performs global temporal attention on top of spatial attention in a decoupled manner.

Action Recognition Action Understanding

Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle

no code implementations10 Jan 2020 Qilei Zhang, Jinying Lin, Qixin Sha, Bo He, Guangliang Li

In this paper, we proposed a deep interactive reinforcement learning method for path following of AUV by combining the advantages of deep reinforcement learning and interactive RL.

reinforcement-learning

Improving Interactive Reinforcement Agent Planning with Human Demonstration

no code implementations18 Apr 2019 Guangliang Li, Randy Gomez, Keisuke Nakamura, Jinying Lin, Qilei Zhang, Bo He

Our results show that learning from demonstration can allow a TAMER agent to learn a roughly optimal policy up to the deepest search and encourage the agent to explore along the optimal path.

reinforcement-learning

HSR: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection

no code implementations23 Sep 2014 Bo Han, Bo He, Tingting Sun, Mengmeng Ma, Amaury Lendasse

By employing hierarchical feature selection, we can compress the scale and dimension of global dictionary, which directly contributes to the decrease of computational cost in sparse representation that our approach is strongly rooted in.

Face Recognition Sparse Representation-based Classification

Robust OS-ELM with a novel selective ensemble based on particle swarm optimization

no code implementations13 Aug 2014 Yang Liu, Bo He, Diya Dong, Yue Shen, Tianhong Yan, Rui Nian, Amaury Lendase

Second, an adaptive selective ensemble framework for online learning is designed to balance the robustness and complexity of the algorithm.

General Classification online learning

LARSEN-ELM: Selective Ensemble of Extreme Learning Machines using LARS for Blended Data

no code implementations9 Aug 2014 Bo Han, Bo He, Rui Nian, Mengmeng Ma, Shujing Zhang, Minghui Li, Amaury Lendasse

Extreme learning machine (ELM) as a neural network algorithm has shown its good performance, such as fast speed, simple structure etc, but also, weak robustness is an unavoidable defect in original ELM for blended data.

RMSE-ELM: Recursive Model based Selective Ensemble of Extreme Learning Machines for Robustness Improvement

no code implementations9 Aug 2014 Bo Han, Bo He, Mengmeng Ma, Tingting Sun, Tianhong Yan, Amaury Lendasse

It becomes a potential framework to solve robustness issue of ELM for high-dimensional blended data in the future.

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