SST: Single-Stream Temporal Action Proposals

By Shyamal Buch, Victor Escorcia, Chuanqi Shen, Bernard Ghanem, Juan Carlos Niebles. 2017

445 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

RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “To reduce the number of proposals, Buch et al. (2017) proposed a single-stream temporal action proposal generation method that does not the need to”
Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization (2017, background): “In the same spirit, contemporary works [4,14,17] produce action proposals by exploiting the effectiveness of deep neural networks.”
Weakly Supervised Action Localization by Sparse Temporal Pooling Network (2017, methodology): “To facilitate action detection and localization, many algorithms use action proposals [4, 7, 38], which is an extension of object proposals for object detection in images.”
End-to-End Dense Video Captioning with Masked Transformer (2018, unknown): “More recently, inspired by the anchoring mechanism from object detection [25], two types of methods have been proposed— explicit anchoring [11, 42] and implicit anchoring [8, 4].”
G-TAD: Sub-Graph Localization for Temporal Action Detection (2019, methodology): “For proposal generation, they either use fixed handcrafted anchors [5, 6, 13, 15, 37] , or adaptively form proposal candidates by connecting potential start and end frames [56, 30].”
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos (2018, methodology): “We draw inspiration from prior work in action localization [7] for our experiment design.”
Graph Convolutional Networks for Temporal Action Localization (2019, unknown): “[2] - - 37.”
SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition (2019, background): “Action localization is often approached through a two-step mechanism [5, 8, 5, 14, 15, 21, 28, 1], where first an action proposal method identifies candidate action segments, and then a more sophisticated approach validates the class of each candidate and refines its temporal boundaries.”
Diagnosing Error in Temporal Action Detectors (2018, methodology): “Interestingly, all the methods tackled the problem in a two-stage fashion, using a proposal method [2,9,12,6,34] followed by a classification scheme [38,39,40].”
Temporally Grounding Natural Sentence in Video (2018, methodology): “As shown in Figure 2, at each time step t, the grounder efficiently scores a set of K grounding candidates by considering multiple time scales (Buch et al., 2017) that end at time step t.”
Listen to Look: Action Recognition by Previewing Audio (2019, background): “Many approaches [8, 79, 40, 68] first use action proposals to identify candidate action segments.”
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization (2017, background): “These datasets have substantially advanced the progress of research on action proposal generation [17, 18, 5, 35] and action localization [59, 48, 61, 34, 9, 2, 4].”
Rethinking the Faster R-CNN Architecture for Temporal Action Localization (2018, methodology): “Inspired by the recent success of region-based detectors in object detection [18, 17], many recent approaches adopt a two-stage, proposal-plus-classification framework [6, 36, 12, 3, 4, 35, 56], i.”
Gaussian Temporal Awareness Networks for Action Localization (2019, methodology): “Approach THUMOS14 ActivityNet ActivityNet (test server) AR AR AUC AUC SST [3] 37.”
Dense Procedure Captioning in Narrated Instructional Videos (2019, background): “SST in (Buch et al., 2017) effectively generates proposals in a single pass.”
ActionFormer: Localizing Moments of Actions with Transformers (2022, methodology): “encoder input clip T×D projection1 conv k=3, s=1 (ci = D, co = 512) input clip T × 512 projection2 conv k=3, s=1 (ci = 512, co = 512) projection1 T × 512 transformer0 Transformer Unit, ds=1 projection2 T × 512 transformer1 Transformer Unit, ds=1 transformer0 T × 512 [0, 4) transformer2 Transformer U”
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation (2018, methodology): “Recently some methods [4,5,9,13,32] generate proposals with pre-defined temporal durations and intervals, and use multiple methods to evaluate the confidence score of proposals, such as dictionary learning [5] and recurrent neural network [9].”
Graph Distillation for Action Detection with Privileged Modalities (2017, background): “The field of action classification [3,50,52] and action detection [2,11,14,65] in RGB videos has been studied by the computer vision community for decades.”