mlsanityData to 14 Oct 2026

QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024

arXiv 2407.04184 ↗First posted 4 Jul 2024cs.CVcited by 4

On the map: State-space sequence models (S4, Mamba) → Core SSM architectures for language

Abstract (arXiv)

This report presents a novel Mamba-based encoder-decoder architecture, QueryMamba, featuring an integrated verb-noun interaction module that utilizes a statistical verb-noun co-occurrence matrix to enhance video action forecasting. This architecture not only predicts verbs and nouns likely to occur based on historical data but also considers their joint occurrence to improve forecast accuracy. The efficacy of this approach is substantiated by experimental results, with the method achieving second place in the Ego4D LTA challenge and ranking first in noun prediction accuracy.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 12 of its 14 references that are in the map. First posted on arXiv 4 Jul 2024.

Builds on

12 of 14 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spaces1 Dec

Other references · 11

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  4. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  5. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  6. 2021Anticipative Video Transformercited by 200
  7. 2018When will you do what? - Anticipating Temporal Occurrences of Activitiescited by 107
  8. 2022Future Transformer for Long-term Action Anticipationcited by 58
  9. 2022InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challengescited by 48
  10. 2023Memory-and-Anticipation Transformer for Online Action Understandingcited by 39
  11. 2023DiffAnt: Diffusion Models for Action Anticipationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024QMambaBSR: Burst Image Super-Resolution with Query State Space Modelcited by 27
  2. 2025Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025cited by 9
  3. 2025Vision and Intention Boost Large Language Model in Long-Term Action Anticipationcited by 5
  4. 2026Reliable Egocentric Action Anticipation via Temporal Reliability Suppression and Compositional Graph Decodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023
  2. 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
  3. 2024Mamba Fusion: Learning Actions Through Questioning
  4. 2024ReMamba: Equip Mamba with Effective Long-Sequence Modeling
  5. 2025VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining
  6. 2026TurboMamba: Faster Inference, Faster Training, and Better Prediction with Lexical Memory
  7. 2024A Survey of Mamba
  8. 2024Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints