Computer vision

Onfocus detection: identifying individual-camera eye contact from unconstrained images
Onfocus detection aims at identifying whether the focus of the individual captured by a camera is on the camera or not. Based on the …
PDF Cite
Robust Region Feature Synthesizer for Zero-Shot Object Detection
Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes …
PDF Cite
Scribble-Supervised Video Object Segmentation
Recently, video object segmentation has received great attention in the computer vision community. Most of the existing methods heavily …
PDF Cite
Strengthen Learning Tolerance for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims at learning to localize objects of interest by only using the image-level labels as …
PDF Cite
Learning Object Detectors with Semi-Annotated Weak Labels
For alleviating the human labor associated with annotating the training data for learning object detectors, recent research has focused …
PDF Cite
Revisiting anchor mechanisms for temporal action localization
Most of the current action localization methods follow an anchor-based pipeline depicting action instances by pre-defined anchors, …
PDF Cite
Segmentation in weakly labeled videos via a semantic ranking and optical warping network.
Weakly supervised video object segmentation (WSVOS) focuses on generating pixel-level object masks for videos only tagged with class …
PDF Cite
Reinforcement cutting-agent learning for video object segmentation
Video object segmentation is a fundamental yet challenging task in computer vision community. In this paper, we formulate this problem …
PDF Cite
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
Motion of the human body is the critical cue for understanding and characterizing human behavior in videos. Most existing approaches …
PDF Cite
Spftn: A self-paced fine-tuning network for segmenting objects in weakly labelled videos
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform …
PDF Cite