paper-with-me

Papers

Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022

2022-11-16 · Yin-Dong Zheng, Guo Chen, Jiahao Wang, Tong Lu, LiMin Wang

Capturing the state changes of interacting objects is a key technology for understanding human-object interactions. This technical report describes our method using heterogeneous backbones for the Ego4D Object State Change Classification and PNR Temporal Localization Challenge. In the challenge, we used the heterogeneous video understanding backbones, namely CSN with 3D convolution as operator and VideoMAE with Transformer as operator. Our method achieves an accuracy of 0.796 on OSCC while achieving an absolute temporal localization error of 0.516 on PNR. These excellent results rank 1st on the leaderboard of Ego4D OSCC & PNR-TL Challenge 2022.

📄 PDF Abstract BibTeX arXiv:2211.08728

Code (0)

등록된 구현이 없습니다.

Tasks

Human-Object Interaction DetectionObjectObject State Change ClassificationTemporal LocalizationVideo Understanding

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways

2026-08-13 · Mao Jiayang, Wang Lanfeng, Peng Zhao-Han arxiv

Heterogeneous USV cooperative pursuit in constrained port waterways requires evader interception under navigation, traffic, and role constraints. This paper proposes OGR-MARL, an option-guided residual multi-agent reinfo…

Multi-agent Reinforcement Learning

InLINE: Inner-Layer Information Exchange for Multi-task Learning on Heterogeneous Graphs

2024-10-29 · Xinyue Feng, Jinquan Hang, Yuequn Zhang, Haotian Wang 외

Heterogeneous graph is an important structure for modeling complex relational data in real-world scenarios and usually involves various node prediction tasks within a single graph. Training these tasks separately may neg…

DisentanglementMulti-Task Learning

Exploring Historical Information for RGBE Visual Tracking with Mamba

2025-01-01 · CVPR 2025 1 · Chuanyu Sun, Jiqing Zhang, Yang Wang, Huilin Ge 외

Combining the advantages of conventional and event cameras for robust visual tracing has drawn extensive interest. However, existing tracking approaches heavily engage in complex cross-modal fusion modules, leading t…

DecoderLong-range modelingMambaVisual Tracking

Exploring Temporally-Aware Features for Point Tracking

2025-01-21 · CVPR 2025 1 · Inès Hyeonsu Kim, Seokju Cho, Jiahui Huang, Jung Yi 외

Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve generalizability, point tracking has pr…

Point TrackingVideo Editing

Heterogeneous Graph Tree Networks

2022-09-01 · Nan Wu, Chaofan Wang

Heterogeneous graph neural networks (HGNNs) have attracted increasing research interest in recent three years. Most existing HGNNs fall into two classes. One class is meta-path-based HGNNs which either require domain kno…

Node Classification