Streaming Hierarchical Video Segmentation

By Chenliang Xu, Caiming Xiong, Jason J. Corso. 2012

262 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

Citations in the corpus

• Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity (2022, neutral): “, [1, 4, 6, 18, 51, 58]), before deep learning for supervised object detection took off, were quite category-agnostic.”
• Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions (2013, unknown): “Methods like [9, 3, 11, 22] present efficient optimization frameworks for spatiotemporal grouping of pixels for video segmentation.”
• Saliency-Aware Video Object Segmentation (2018, unknown): “Utilizing both motion and appearance cues seems to be a better choice as it was adopted by many methods [4], [5], [6], [7], [8], [9].”
• Click Carving: Segmenting Objects in Video with Point Clicks (2016, unknown): “Whereas conventional interactive pipelines take the user’s initialization as a starting point, we show the value in the system taking the lead even in initialization.”
• Unsupervised Discovery of Parts, Structure, and Dynamics (2019, unknown): “There have been also extensive research on hierarchical motion decomposition (Ross & Zemel, 2006; Ross et al., 2010; Grundmann et al., 2010; Xu et al., 2012; Flores-Mangas & Jepson, 2013; Jain et al., 2014; Ochs et al., 2014; Pérez-Rúa et al., 2016; Gershman et al., 2016; Esmaeili et al., 2018).”
• A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis (2013, unknown): “Graph-based [13, 29] and meanshift techniques [20] are based on local properties and usually focus on generating an over-segmentation of a video.”
• Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation (2014, unknown): “Image GT [14] [12] G ≡ G NCut G ≡ G′ SC [29] Stream(500) G Figure 7.”
• Optical Flow with Semantic Segmentation and Localized Layers (2016, unknown): “There is significant and increasing interest in the field [12, 14, 32, 41, 42, 57] but the definition of the problem varies between identifying coherent motions or coherent objects regions.”
• SegFlow: Joint Learning for Video Object Segmentation and Optical Flow (2017, unknown): “Several methods have been proposed to generate object segmentation via saliency [31, 11, 42], optical flow [4, 28] or superpixel [17, 46, 13].”
• Spatio-temporal Object Detection Proposals (2014, unknown): “A streaming version of GBH was introduced in [47], which performs similar to GBH, but at a fraction of the cost by using overlapping temporal windows of the video to optimize the segmentation.”
• Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, unknown): “However, most methods either attempt to group pixels from all frames [19, 57, 11] or track regions that are initialized from arbitrary frames (e.”
• Action Localization with Tubelets from Motion (2014, unknown): “Super-voxels give excellent boundary recall [3, 34, 35] for non-rigid objects.”
• Video Segmentation via Object Flow (2016, unknown): “Furthermore, we generate superpixels by utilizing supervoxels [13, 42] between two frames to exploit temporal information in addition to the use of optical flow.”
• Online Video SEEDS for Temporal Window Objectness (2013, unknown): “Recently, Xu et al. [16] [17] proposed a benchmark to evaluate video superpixels and a framework for streaming video segmentation using the graph-based superpixel approach of [5].”
• Video Segmentation by Tracking Many Figure-Ground Segments (2013, unknown): “Many state-of-the-art approaches are based on the agglomerative clustering approach on supervoxels [16, 15, 37, 18]; spatial-temporal graph-cuts [36]; or tracking feature points or local regions [6, 34, 7].”
• Saliency-aware geodesic video object segmentation (2015, unknown): “Some efforts [5, 26, 30] presented efficient optimization frameworks for bottom-up final segmentation employing both appearance and motion cues.”
• FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (2017, unknown): “In recent years, video object segmentation has received significant attention, with great progress on fully automatic algorithms [15, 56, 13, 23, 30, 58, 24, 35, 10], propagation methods [40, 47, 11, 50, 19, 53], and interactive methods [51, 26, 2, 42].”
• Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation (2018, unknown): “Prior to the prevalence of deep learning, most approaches to semantic video segmentation are graph based [8, 18, 36, 25].”
• Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering (2014, unknown): “, S∗ N} ∈ S (where N is the number of visual objects), minimizer of an objective function, implicit [20, 47, 37] or explicit [39, 34, 43, 10].”