Ieee Transactions on Pattern Analysis and Machine Intelligence Segmentation of Moving Objects by Long Term Video Analysis

By Peter Ochs, Jitendra Malik, Thomas Brox. 2014

653 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

Learning Features by Watching Objects Move (2016, methodology): “Figure 7 shows the output of the ConvNet on frames from the DAVIS [33], FBMS [28] and VSB [11] datasets, which were not used in training.”
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks (2016, methodology): “Motion Segmentation: We report results using [19, 14] on the training set of FBMS-59 [27, 19] with a density of 4 pixels.”
YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark (2018, methodology): “In comparison to previous datasets [16,21,22,23,24,25], DAVIS has both higher-quality of video resolutions and annotations.”
One-Shot Video Object Segmentation (2016, methodology): “In the former we compare to OFL [49], BVS [33], LTV [35], HBT [16], AFS [50], SCF [20], and JFS [45].”
Video Instance Segmentation (2019, methodology): “YTO [13] FBMS [20] DAVIS [22, 23] YTVOS [34] YTVIS”
Learning Unsupervised Video Object Segmentation Through Visual Attention (2019, background): “Early UVOS methods are typically based on handcrafted features and heuristics such as long-term point trajectory [54, 5, 17, 53, 9], motion boundary [56], objectness [43, 51, 89, 18, 59, 83, 40, 45], and saliency [13, 77, 76, 34, 27].”
Video Segmentation via Object Flow (2016, methodology): “Category [22] [14] [36] [12] [24] [23] Ours”
MODNet: Motion and Appearance based Moving Object Detection Network for Autonomous Driving (2018, background): “Although there exists other motion segmentation datasets such as [21][17][19].”
Eye tracking assisted extraction of attentionally important objects from videos (2015, methodology): “[32] Papazoglou”
Unsupervised Discovery of Parts, Structure, and Dynamics (2019, background): “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).”
Long-Term Image Boundary Prediction (2016, methodology): “We report quantitative results for prediction one time-step into the future (as in (Srivastava, Mansimov, and Salakhutdinov 2015; Patraucean, Handa, and Cipolla 2015)) in Table 7 using the Cross Entropy Loss (Srivastava, Mansimov, and Salakhutdinov 2015).”
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, methodology): “Although videos from SegTrack [21] and FBMS [43], [44] databases span a large range of difﬁculties, the amount Fig.”
AMP: Adaptive Masked Proxies for Few-Shot Segmentation (2019, methodology): “AMP is evaluated on PASCAL-5i [28], DAVIS benchmark [22], FBMS [20] and our proposed iPASCAL setup.”
The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation (2019, methodology): “In order to account for the latter, [42] re-annotated the datasets of [37], [38], [39] and re-deﬁned the task to take into account object motion instead of single-pixel motion.”
Instance Embedding Transfer to Unsupervised Video Object Segmentation (2018, methodology): “We evaluate the proposed method on the DAVIS dataset [33], Freiburg-Berkeley Motion Segmentation (FBMS) dataset [30], and the SegTrack-v2 dataset [23].”
A Survey of Deep Learning-Based Object Detection (2019, neutral): “Video salient object detection datasets [223][224][225][226][227][228][229]”
MOTS: Multi-Object Tracking and Segmentation (2019, methodology): “In addition, the Segtrackv2 [28] dataset, FBMS [40] and an annotated subset of the YouTube-Objects dataset [46, 19] can be used to evaluate this task.”
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation – A Synthetic Dataset and Baselines (2019, background): “It is therefore not surprising that ﬁrst datasets, which focus on a single object per video, didn’t appear until recently [97, 80, 71, 28, 76].”
Shifting More Attention to Video Salient Object Detection (2019, methodology): “Second, with the established DAVSOD dataset and previous 7 VSOD datasets [35,40,43,52,56,59,75], we present a comprehensive evaluation of 17 state-of-the-art models [8, 11,35,41,44,52,53,62,67,68,70,74–76,81,87,92], making it the most complete VSOD benchmark.”