Log In Sign Up

Triple-cooperative Video Shadow Detection

by   Zhihao Chen, et al.

Shadow detection in a single image has received significant research interest in recent years. However, much fewer works have been explored in shadow detection over dynamic scenes. The bottleneck is the lack of a well-established dataset with high-quality annotations for video shadow detection. In this work, we collect a new video shadow detection dataset, which contains 120 videos with 11, 685 frames, covering 60 object categories, varying lengths, and different motion/lighting conditions. All the frames are annotated with a high-quality pixel-level shadow mask. To the best of our knowledge, this is the first learning-oriented dataset for video shadow detection. Furthermore, we develop a new baseline model, named triple-cooperative video shadow detection network (TVSD-Net). It utilizes triple parallel networks in a cooperative manner to learn discriminative representations at intra-video and inter-video levels. Within the network, a dual gated co-attention module is proposed to constrain features from neighboring frames in the same video, while an auxiliary similarity loss is introduced to mine semantic information between different videos. Finally, we conduct a comprehensive study on ViSha, evaluating 12 state-of-the-art models (including single image shadow detectors, video object segmentation, and saliency detection methods). Experiments demonstrate that our model outperforms SOTA competitors.


page 2

page 4

page 5

page 8

page 11


VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection

Lane detection plays a key role in autonomous driving. While car cameras...

Temporal Feature Warping for Video Shadow Detection

While single image shadow detection has been improving rapidly in recent...

Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from Images

Deep learning based object detectors require thousands of diversified bo...

Revisiting Video Saliency: A Large-scale Benchmark and a New Model

In this work, we contribute to video saliency research in two ways. Firs...

Free Lunch for Co-Saliency Detection: Context Adjustment

We unveil a long-standing problem in the prevailing co-saliency detectio...

DeepApple: Deep Learning-based Apple Detection using a Suppression Mask R-CNN

Robotic apple harvesting has received much research attention in the pas...

SCOTCH and SODA: A Transformer Video Shadow Detection Framework

Shadows in videos are difficult to detect because of the large shadow de...

Code Repositories


Code for the CVPR 2021 paper "Triple-cooperative Video Shadow Detection"

view repo