In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
원문 초록
In this paper, we present the first transformer-based model to address the challenging problem of egocentric gaze estimation. We observe that the connection between the global scene context and local visual information is vital for localizing the gaze fixation from egocentric video frames. To this end, we design the transformer encoder to embed the global context as one additional visual token and further propose a novel Global-Local Correlation (GLC) module to explicitly model the correlation of the global token and each local token. We validate our model on two egocentric video datasets - EGTEA Gaze+ and Ego4D. Our detailed ablation studies demonstrate the benefits of our method. In addition, our approach exceeds previous state-of-the-arts by a large margin. We also provide additional visualizations to support our claim that global-local correlation serves a key representation for predicting gaze fixation from egocentric videos. More details can be found in our website (https://bolinlai.github.io/GLC-EgoGazeEst).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Inference-Time Gaze Refinement for Micro-Expression Recognition: Enhancing Event-Based Eye Tracking with Motion-Aware Post-Processing
Trade-offs in Privacy-Preserving Eye Tracking through Iris Obfuscation: A Benchmarking Study
Adapting Robot's Explanation for Failures Based on Observed Human Behavior in Human-Robot Collaboration
Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer
SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
Upper-Body Pose-based Gaze Estimation for Privacy-Preserving 3D Gaze Target Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.