The Action Similarity Labeling Challenge

By Orit Kliper-Gross, Tal Hassner, Lior Wolf. 2012

134 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

C3D: Generic Features for Video Analysis (2014, methodology): “Performance STIP [27] OSSML [28] MIP [26] MIP+STIP+MBH [16] iDT+FV [53] Random Chance Dataset .”
Survey on 3D Hand Gesture Recognition (2016, background): “Among numerous public data sets2,3,4 in vision field, both 2D [82], [83] and 3D [84] human action data sets have been provided for body gesture research.”
Human Action Recognition From Various Data Modalities: A Review (2020, unknown): “Dataset Reference Year Modality #Class #Subject #Sample #View KTH [402] 2004 RGB 6 25 2,391 1 Weizmann [66] 2005 RGB 10 9 90 1 IXMAS [70] 2006 RGB 11 10 330 5 HDM05 [403] 2007 RGB,S 130 5 2,337 1 Hollywood [87] 2008 RGB 8 430 Hollywood2 [404] 2009 RGB 12 - 3,669 MSR-Action3D [254] 2010 S,D 20 10 567”
ConvNet Architecture Search for Spatiotemporal Feature Learning (2017, methodology): “The ASLAN dataset[16] has 3,631 videos from 432 action classes.”
Evaluation of video activity localizations integrating quality and quantity measurements (2014, background): “Consequently, we see an early drop in performance varying any one of the thresholds, t sr = 1 or t sp = 1 .”
One Shot Similarity Metric Learning for Action Recognition (2011, methodology): “Here, we report attempts to employ OSS on the recently introduced “Action Similarity Labeling” (ASLAN) data set [12], which includes thousands of videos from the web, in over 400 complex action classes.”
A Critical Review of Action Recognition Benchmarks (2013, methodology): “Two very recent examples include [3, 12] and [19].”
Human Action Recognition and Prediction: A Survey (2018, unknown): “ASLAN (Kliper-Gross et al., 2012) 2012 3,698 – 432 – RGB Uncontrolled”
Evaluating New Variants of Motion Interchange Patterns (2013, methodology): “The Action Similarity Labeling (ASLAN) benchmark [12] is a large-scale benchmark containing thousands of video clips collected from YouTube and over 400 complex action classes.”
Violent flows: Real-time detection of violent crowd behavior (2012, methodology): “For a recent, comprehensive survey of such benchmarks, see [16].”
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks (2017, methodology): “The performance comparisons on ASLAN are shown in Table 5.”
From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding (2013, background): “Recently, there have been efforts to collect large datasets from consumer sources to address these issues [17, 23, 16].”
Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics (2019, methodology): “It outperforms the handcrafted features STIP [21], which is the combination of three popular features: HOG, HOF, and HNF (a composition of HOG and HOF).”
Video Segmentation by Non-Local Consensus voting (2014, methodology): “We tested our algorithm on various datasets, ranging from benchmark evaluation datasets (SegTrack [21, 35]), on which we empirically compared results to others, to more difficult video sequences (taken from human action datasets like UCF101 [32] and ASLAN [19]), on which current state-of-the-art met”
Large Margin Dimensionality Reduction for Action Similarity Labeling (2014, methodology): “Models (GMM) and pool them to yield video-level representations; iii) we apply the proposed LMDRmethod to project these representations to a discriminative subspace; iv) we transform the two compact video representations to a single video-pair representation by performing point-wise multiplications,”
Motion Interchange Patterns for Action Recognition in Unconstrained Videos (2012, methodology): “The Action Similarity Labeling (ASLAN) collection [12] is a recent Action Recognition benchmark, which is modeled similarly to the Labeled Faces in the Wild face identification dataset [27].”
Learning Spatiotemporal Features with 3D Convolutional Networks (2014, methodology): “C3D Human Performance STIP [21] OSSML [22] MIP [20] MIP+STIP+MBH [11] iDT+FV [44] Imagenet Random Chance”