Representing Videos Using Mid-level Discriminative Patches

By Arpit Jain, Abhinav Kumar Gupta, Mikel D. Rodriguez, Larry S. Davis. 2013

155 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

Joint Discovery of Object States and Manipulation Actions (2017, background): “Such methods can incorporate (weak) supervision that helps to steer the clustering towards a preferred solution [5, 13, 21, 24, 42].”
Delving into Egocentric Actions (2015, neutral): “Jain et al. [11] demonstrate that mid-level discriminative patches can be mined from video, and used for classification as well as building correspondences between videos.”
Learning to Explain With Complemental Examples (2018, background): “Prototype selection [25, 7, 13, 16, 25, 10] or machine teaching [18] can be considered as example-based explanations.”
Actions ~ Transformations (2015, background): “Mid-to high-level representation are also used to model complex actions [41, 55, 36, 60, 14, 24].”
Context as Supervisory Signal: Discovering Objects with Predictable Context (2014, background): “A number of recent works have argued that weak supervision can be an effective way to get more visually meaningful clusters [14,15,16,17,18,19,20,21,22,23].”
Temporal Segment Networks for Action Recognition in Videos (2017, background): “mid-level representations have been proposed for action recognition [3], [23], [47], [48], [49], [50], [51].”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Recently there has been a push towards mid-level representations of video [37, 46, 13, 20], that capture beyond local properties.”
Action Recognition by Hierarchical Mid-Level Action Elements (2015, unknown): “1.”
Mid-level Visual Element Discovery as Discriminative Mode Seeking (2013, methodology): “, scene categories [12] or GPS coordinates [5] (but can also run unsupervised [23]), and have been recently used for tasks including image classification [12, 23, 27], object detection [6], visual data mining [5, 15], action recognition [11], and geometry estimation [7].”
Learning Mid-level Filters for Person Re-identification (2014, background): “[8] learned mid-level features in scene classiﬁcation and action recognition by patch clustering and measuring of the purity and discriminativeness with detection scores.”
Discriminative Orderlet Mining for Real-Time Recognition of Human-Object Interaction (2014, background): “It is impossible to list them all, and we only mention a few [25, 26, 28–30, 10, 11, 31, 32].”
Listen to Look: Action Recognition by Previewing Audio (2019, methodology): “Research has transitioned from initial methods using hand-crafted local spatiotemporal features [35, 66, 61] to mid-level descriptors [46, 29, 62], and more recently to deep video representations learned end-to-end [50, 30, 16].”
ConceptMap: Mining Noisy Web Data for Concept Learning (2014, unknown): “[34] [50] [27] [50,9,8,25,10,26,35,7].”
Selective clustering for representative paintings selection (2019, background): “[18] proposed to represent videos based on mid-level discriminative spatial-temporal patches.”
Activity Auto-Completion: Predicting Human Activities from Partial Videos (2015, background): “Recently, some works focus on extracting mid-level features [5, 21, 10, 24, 11, 2].”
Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models (2014, background): “Recently, discriminatively trained mid-level representations have shown great promise for various visual recognition tasks, both in a supervised regime [6], as well as unsupervised [22, 23, 36], including 2D-to-3D alignment of object instances across large changes in appearance [4].”
Viewpoint-Aware Video Summarization (2018, methodology): “We also acknowledge methods for discovering mid-level discriminative patches [35, 22, 15, 3, 4, 5] as related works because it attempts to find representative and discriminative elements from grouped data.”