mlsanityData to 14 Oct 2026

Spatial-temporal Concept based Explanation of 3D ConvNets

arXiv 2206.05275 ↗First posted 9 Jun 2022cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Recent studies have achieved outstanding success in explaining 2D image recognition ConvNets. On the other hand, due to the computation cost and complexity of video data, the explanation of 3D video recognition ConvNets is relatively less studied. In this paper, we present a 3D ACE (Automatic Concept-based Explanation) framework for interpreting 3D ConvNets. In our approach: (1) videos are represented using high-level supervoxels, which is straightforward for human to understand; and (2) the interpreting framework estimates a score for each voxel, which reflects its importance in the decision procedure. Experiments show that our method can discover spatial-temporal concepts of different importance-levels, and thus can explore the influence of the concepts on a target task, such as action classification, in-depth. The codes are publicly available.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

27 of 45 references.

References · 27

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  10. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  11. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
15 more
  1. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  2. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  3. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  4. 2017Residual Attention Network for Image Classificationcited by 386
  5. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 310
  6. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  7. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  8. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  9. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  10. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  11. 2019Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networkscited by 49
  12. 2021A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Conceptscited by 33
  13. 2019Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutionscited by 20
  14. 2016Hierarchical Attention Network for Action Recognition in Videoscited by 8
  15. 2021Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderingscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 7.

12 papers.

  1. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  2. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 18
  3. 2023State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understandingcited by 17
  4. 2024Natural Language Reinforcement Learningcited by 17
  5. 2024Natural Language Reinforcement Learningcited by 5
  6. 2025On The Variability of Concept Activation Vectorscited by 3
  7. 2025Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognitioncited by 2
  8. 2025PCBEAR: Pose Concept Bottleneck for Explainable Action Recognitioncited by 1
  9. 2025LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanationscited by 1
  10. 2025Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classificationcited by 1
  11. 2025TraNCE: Transformative Non-linear Concept Explainer for CNNscited by 0
  12. 2025ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networkscited by 0