Related papers: Action Duration Prediction for Segment-Level Align…
Frame-by-frame annotation of bounding boxes by clinical experts is often required to train fully supervised object detection models on medical video data. We propose a method for improving object detection in medical videos through weak…
This paper addresses the problem of real-time action recognition in trimmed videos, for which deep neural networks have defined the state-of-the-art performance in the recent literature. For attaining higher recognition accuracies with…
Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train…
In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for…
Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames. Despite these methods having superior performance, they suffer from…
We segment moving objects in videos by ranking spatio-temporal segment proposals according to "moving objectness": how likely they are to contain a moving object. In each video frame, we compute segment proposals using multiple…
Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle…
Video prediction has been an active topic of research in the past few years. Many algorithms focus on pixel-level predictions, which generates results that blur and disintegrate within a few frames. In this project, we use a hierarchical…
Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…
We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods…
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…
In this paper, we propose an end-to-end 3D CNN for action detection and segmentation in videos. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. A video is…
We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents…
Many believe that the successes of deep learning on image understanding problems can be replicated in the realm of video understanding. However, due to the scale and temporal nature of video, the span of video understanding problems and the…
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the…
In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, our approach…
Video moment retrieval aims to localize the target moment in an video according to the given sentence. The weak-supervised setting only provides the video-level sentence annotations during training. Most existing weak-supervised methods…
Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides…
In this paper, we address the challenging problem of spatial and temporal action detection in videos. We first develop an effective approach to localize frame-level action regions through integrating static and kinematic information by the…
The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning…