Actions as space-time shapes

By Moshe Blank, Lena Gorelick, Eli Shechtman, Michal Irani, Ronen Basri. 2005

2,436 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild (2012, background): “…action recognition datasets suffer from two disadvantages: 1) The number of their classes is typically very low compared to the richness of performed actions by humans in reality, e.g. KTH [11], Weizmann [3], UCF Sports [10], IXMAS [12] datasets includes only 6, 9, 9, 11 classes respectively.”
HMDB: A large video database for human motion recognition (2011, background): “State-of-the-art performance on these datasets is now near ceiling and thus there is a need for the design and creation of new benchmarks.”
YouTube-8M: A Large-Scale Video Classification Benchmark (2016, background): “…understanding domain where the community has quickly progressed from small, well-labeled datasets such as KTH [22], Hollywood 2 [23], Weizmann [5], with a few thousand video clips, to medium-scale datasets such as UCF101 [33], Thumos‘14 [16] and HMDB51 [21], with more than 50 action…”
AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions (2017, background): “Most popular action clas-siﬁcation datasets, such as KTH [35], Weizmann [4], Hollywood-2 [26], HMDB [24], UCF101 [39] consist of short clips, manually trimmed to capture a single action.”
A survey on data fusion in internet of things: Towards secure and privacy-preserving fusion (2019, methodology): “N N N [63] Activity recognition Camera data Weighted feature fusion Weizmann Dataset[72], MuHAVi Dataset[73], IXMAS Dataset[74] N Y 95.2 - - - - - - - -”
RGB-D-based action recognition datasets: A survey (2016, background): “The first 10 categories follow the same definitions as the Weizmann action dataset [19] and the 11–16th actions are extended categories.”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, background): “Since HOPC and STK-Distribution capture complimentary information, their combination significantly improves classification accuracy which is over 22% higher than the nearest competitor on both datasets.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, methodology): “In RGB videos, in order to recognize actions across viewpoint changes, mostly view independent representations are proposed such as view invariant spatio-temporal features [2,20,22,23,25,33].”
C3D: Generic Features for Video Analysis (2014, background): “The computer vision community has been working on video analysis for decades and tackled different problems such as action recognition [2, 31, 40], abnormal event detection [3, 7, 55], and activity understanding [29].”
Finding action tubes (2014, background): “[3] use spatio-temporal volume silhouettes to describe an action assuming in addition known background.”
Video In Sentences Out (2012, methodology): “For example, the Weizmann dataset [Blank et al., 2005] and the kth dataset [Schuldt et al.”
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos (2015, background): “land et al. [48]. Here we review recent work relevant to dense labeling of videos. 2.1 Datasets Research focus is closely intertwined with dataset creation and availability. The KTH [33] and Weizmann [2] datasets were catalysts for a body of work. This era focused on recognizing individual human act”
MoCoGAN: Decomposing Motion and Content for Video Generation (2017, methodology): “We used the Weizmann Action database [13], containing 81 videos of 9 people performing 9 actions, including jumping-jack and waving-hands.”
Video Action Transformer Network (2018, background): “ work. 2. Related Work Video Understanding: Video activity recognition has evolved rapidly in recent years. Datasets have become progressively larger and harder: from actors performing simple actions [12,33], to short sports and movie clips [24,38], ﬁnally to diverse youtube videos [1,23]. Models ha”
End-to-End Learning of Action Detection from Frame Glimpses in Videos (2015, background): “Our goal is to take a long sequence of video and output any instances of a given action.”
Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks (2015, background): “Since video sequences can naturally be viewed as three-dimensional (3D) spatio-temporal signals, many existing methods seek to develop different spatiotemporal features for representing spatially and temporally coupled action patterns [12, 31, 8, 5].”