mlsanityData to 14 Oct 2026

UnweaveNet: Unweaving Activity Stories

arXiv 2112.10194 ↗First posted 19 Dec 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Our lives can be seen as a complex weaving of activities; we switch from one activity to another, to maximise our achievements or in reaction to demands placed upon us. Observing a video of unscripted daily activities, we parse the video into its constituent activity threads through a process we call unweaving. To accomplish this, we introduce a video representation explicitly capturing activity threads called a thread bank, along with a neural controller capable of detecting goal changes and resuming of past activities, together forming UnweaveNet. We train and evaluate UnweaveNet on sequences from the unscripted egocentric dataset EPIC-KITCHENS. We propose and showcase the efficacy of pretraining UnweaveNet in a self-supervised manner.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 19 Dec 2021.

Builds on

36 of 53 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  5. 2017The Kinetics Human Action Video Datasetcited by 1,909
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  7. 2015Pointer Networkscited by 895
  8. 2014Neural Turing Machinescited by 644
  9. 2020Rescaling Egocentric Visioncited by 540
  10. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  11. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 373
  12. 2014Memory Networkscited by 363
24 more
  1. 2019Video Representation Learning by Dense Predictive Codingcited by 175
  2. 2016Video Summarization with Long Short-term Memorycited by 142
  3. 2017CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videoscited by 112
  4. 2020EGO-TOPO: Environment Affordances from Egocentric Videocited by 111
  5. 2015Neural Programmer-Interpreterscited by 101
  6. 2020Compositional Generalization via Neural-Symbolic Stack Machinescited by 80
  7. 2015Inferring Algorithmic Patterns with Stack-Augmented Recurrent Netscited by 76
  8. 2019Unsupervised learning of action classes with continuous temporal embeddingcited by 76
  9. 2018Video Summarization Using Fully Convolutional Sequence Networkscited by 71
  10. 2016Connectionist Temporal Modeling for Weakly Supervised Action Labelingcited by 70
  11. 2021Generic Event Boundary Detection: A Benchmark for Event Segmentationcited by 65
  12. 2020A Local-to-Global Approach to Multi-modal Movie Scene Segmentationcited by 60
  13. 2021Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentationcited by 58
  14. 2015Learning to Transduce with Unbounded Memorycited by 54
  15. 2020Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequencescited by 45
  16. 2018Temporal Gaussian Mixture Layer for Videoscited by 40
  17. 2018A Perceptual Prediction Framework for Self Supervised Event Segmentationcited by 40
  18. 2018Discriminative Feature Learning for Unsupervised Video Summarizationcited by 37
  19. 2015Neural Random-Access Machinescited by 34
  20. 2017The Impact of Random Models on Clustering Similaritycited by 34
  21. 2019Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarizationcited by 24
  22. 2015Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Imagescited by 19
  23. 2015Learning Simple Algorithms from Examplescited by 12
  24. 2015Reinforcement Learning Neural Turing Machines - Revisedcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 2; 2025: 4; 2026: 2.

14 papers.

Sort:

By area:

  1. 2023Affordance Diffusion: Synthesizing Hand-Object Interactionscited by 110
  2. 2024AMEGO: Active Memory from long EGOcentric videoscited by 36
  3. 2022EgoEnv: Human-centric environment representations from egocentric videocited by 22
  4. 2025Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMscited by 19
  5. 2023SpotEM: Efficient Video Search for Episodic Memorycited by 17
  6. 2022Multi-Task Learning of Object State Changes from Uncurated Videoscited by 10
  7. 2024EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videoscited by 8
  8. 2023VideoPro: A Visual Analytics Approach for Interactive Video Programmingcited by 7
  9. 2025HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videoscited by 7
  10. 2026Whareformer: Learning to Track What is Where in Long Egocentric Videoscited by 2
  11. 2023Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Interventioncited by 0
  12. 2025DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videoscited by 0
2 more
  1. 2025The N-Body Problem: Parallel Execution from Single-Person Egocentric Videocited by 0
  2. 2026EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environmentcited by 0