Learning to segment moving objects in videos

By Katerina Fragkiadaki, Pablo Arbeláez, Panna Felsen, Jitendra Malik. 2014

214 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

What Makes for Effective Detection Proposals? (2015, neutral): “F”
Bilinear CNN Models for Fine-Grained Visual Recognition (2015, methodology): ““Two-stream” architectures have been used to analyze video where one networks models the temporal aspect, while the other models the spatial aspect [12, 31].”
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks (2019, background): “For instance, a multi-layer perception based detector was designed in [13] to detect moving”
MODNet: Motion and Appearance based Moving Object Detection Network for Autonomous Driving (2018, methodology): “A recent trend [29][12][4][31][6] for learning motion in videos has emerged.”
Animal Detection From Highly Cluttered Natural Scenes Using Spatiotemporal Object Region Proposals and Patch Verification (2016, unknown): “2) Quantitative Results: We first compare the performance of our animal object proposal method using IEC with the following state-of-the-art object proposal methods: Spatial-Temporal Object Detection Proposals (STODP) [44], Fully Connected Object Proposals for Video Segmentation (FCOP) [43], and Lea”
Deep Curiosity Search: Intra-Life Exploration Improves Performance on Challenging Deep Reinforcement Learning Problems (2018, background): “If one did not have access to RAM states, position could be inferred via object detection [33] or by implicit state-space representations such as Skip Context Tree Switching [34], the latter of which was shown to work well in a roughly similar counting-based model [9].”
See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks (2019, background): “Later, inspired by the success of deep learning, several methods [16, 54, 43] began to approach UVOS using deep learning features.”
Bilinear CNNs for Fine-grained Visual Recognition (2015, methodology): “Our model is related to “two-stream” architectures used to analyze videos where one network models the temporal aspect, while the other models the spatial aspect [17], [58].”
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (2017, methodology): “Second we have the fully automatic methods that generate thousands of “object-like” space-time segments [54, 12, 57, 34, 55].”
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (2016, unknown): “, RGB [7], [8], [10], [11], [13], [20], RGB-D [18], [21], [22], [23], and video [24], [25].”
Saliency-Aware Video Object Segmentation (2018, methodology): “Work of [28] segmented video objects by ranking spatio-temporal segment proposals with moving objectness detector trained on image and motion ﬁelds.”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, methodology): “Finally, unlike [15, 27, 41, 38], which learn to propose objects either in videos or static images, our approach does not require any labeled video/image to train and instead adapts to each unknown object on a per-video basis.”
Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning (2018, methodology): “A recent trend [56, 32, 17, 61, 24] for learning motion in videos has emerged.”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “[113] made an early effort that learns a multi-”
Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video (2018, methodology): “[12] used geodesic [17] and moving object proposals [10], we employ a single-shot detector [19] based on Feature Pyramid Networks (FPN).”
Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories (2019, methodology): “On the other hand, unsupervised methods [4]–[6], [8], [16], [31], [32], [35] segment videos without any human annotation.”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “Using a different approach, Fragkiadaki et al. [38] segments moving objects by regressing the objectness score given RGB image and optical flow.”
A Key Volume Mining Deep Framework for Action Recognition (2016, background): “It may yield better results by utilizing more sophisticated methods [5, 18], but exploring the best proposal methods for action recognition is out of the scope of this paper.”