On Space-Time Interest Points

By Ivan Laptev. 2005

4,050 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

Multiview Transformers for Video Recognition (2022, background): “Early works [34, 37, 73] relied on hand-crafted features to encode motion and appearance information.”
Delving into Egocentric Actions (2015, neutral): “Local spatial-temporal features have been the most prevalent over the past few years [19] [36].”
A Joint Sequence Fusion Model for Video Question Answering and Retrieval (2018, background): “Video classification [14,15,16,17,18] can be a candidate solution, but tagging only a few labels to a video may be insufficient to fully relate multiple latent events in the video to a language description.”
HMDB: A large video database for human motion recognition (2011, background): “In this list, the Hollywood [11] and UCF50 [2] datasets are two examples of recent efforts to build more realistic action recognition datasets by considering video clips taken from real movies and YouTube.”
YouTube-8M: A Large-Scale Video Classification Benchmark (2016, background): “…effort is in progress in the video 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],…”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “The idea of spatio-temporal interest points [26] was applied in depth videos by [79].”
Cross-View Action Modeling, Learning, and Recognition (2014, methodology): “STIP [8] and Action Bank [16] do not perform well on this dataset, either.”
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection (2017, background): “Many traditional works in the field of action recognition focused on designing features to discriminate action classes [19, 44, 5, 18, 17].”
One-shot-learning gesture recognition using HOG-HOF features (2013, background): “Extensions to image sequences have been proposed, the most popular being 1. https://mloss.org/software/view/448 Space-Time Interest Points (Laptev, 2005).”
Action recognition with trajectory-pooled deep-convolutional descriptors (2015, background): “Space Time Interest Points [16] proposed Harris3D detector to extract informative regions, while Cuboid [7] detector relied on temporal Gabor ﬁlters.”
C3D: Generic Features for Video Analysis (2014, methodology): “Laptev and Lindeberg [31] proposed spatio-temporal interest points (STIPs) by extending Harris corner detectors to 3 D. His-togram of Oriented Gradients (HOG) [8] and Histogram of Optical Flows (HOF) [9] are normally extracted at these STIPs and used as video features.”
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition (2014, background): “Note that although we use Improved Dense Trajectory, our methods can be applied to any local features that using differential filters, e.g., STIP [13].”
Actions ~ Transformations (2015, methodology): “Hand-crafted representations have been conventionally used to describe patches centered at Space Time Interest Points (STIP) [26].”
A Closer Look at Spatiotemporal Convolutions for Action Recognition (2017, background): “Some proposed video representations include spatiotemporal interest points (STIPs) [21], SIFT-3D [27], HOG3D [18], Motion Boundary Histogram [5], Cuboids [6], and ActionBank [26].”
Video Action Transformer Network (2018, methodology): “Models have followed suit, from hand-crafted features [25, 42] to deep end-to-end trainable models [7, 22, 43–45].”