# ViewBridge: Curriculum Knowledge Distillation for Activity View-Invariance Under Extreme Viewpoint Changes

arXiv: https://arxiv.org/abs/2504.05451 · HTML: https://mlsanity.com/paper/2504.05451/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 33 of its 57 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 33)

- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Cross-task weakly supervised learning from instructional videos](https://mlsanity.com/paper/1903.08225/) (2019)
- [Dense Regression Network for Video Grounding](https://mlsanity.com/paper/2004.03545/) (2020)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos](https://mlsanity.com/paper/2104.07905/) (2021)
- [Temporal Alignment Networks for Long-term Video](https://mlsanity.com/paper/2204.02968/) (2022)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [My View is the Best View: Procedure Learning from Egocentric Videos](https://mlsanity.com/paper/2207.10883/) (2022)
- [View-Invariant Probabilistic Embedding for Human Pose](https://mlsanity.com/paper/1912.01001/) (2019)
- [LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities](https://mlsanity.com/paper/2007.15781/) (2020)
- [Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment](https://mlsanity.com/paper/2306.05526/) (2023)
- [Temporal Sentence Grounding in Videos: A Survey and Future Directions](https://mlsanity.com/paper/2201.08071/) (2022)
- [Video-Mined Task Graphs for Keystep Recognition in Instructional Videos](https://mlsanity.com/paper/2307.08763/) (2023)
- [Unsupervised Learning of View-invariant Action Representations](https://mlsanity.com/paper/1809.01844/) (2018)
- [On the Benefits of 3D Pose and Tracking for Human Action Recognition](https://mlsanity.com/paper/2304.01199/) (2023)
- [Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos](https://mlsanity.com/paper/2403.06351/) (2024)
- [Learning to Ground Instructional Articles in Videos through Narrations](https://mlsanity.com/paper/2306.03802/) (2023)
- [Localizing Moments in Long Video Via Multimodal Guidance](https://mlsanity.com/paper/2302.13372/) (2023)
- [Comprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluation](https://mlsanity.com/paper/2003.09392/) (2020)
- [ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints](https://mlsanity.com/paper/2112.03905/) (2021)
- [Recognizing Actions in Videos from Unseen Viewpoints](https://mlsanity.com/paper/2103.16516/) (2021)
- [What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis](https://mlsanity.com/paper/1904.07424/) (2019)
- [Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective](https://mlsanity.com/paper/2303.06859/) (2023)

## Abstract (arXiv)

Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with in-the-wild videos that exhibit extreme viewpoint differences and share little visual content. We introduce ViewBridge, a framework for learning rich video representations in the presence of severe view-occlusions. We introduce a knowledge distillation objective that preserves action-centric semantics, together with a novel curriculum learning procedure that pairs incrementally more challenging views over time, thereby allowing smooth adaptation to extreme viewpoint differences. To sort training video segments for the proposed curriculum, we define a geometry-based metric that reflects their likely occlusion level. While training leverages multi-view data, at inference time, the input is an uncalibrated, single-viewpoint video. Evaluating our approach on two tasks -- temporal keystep grounding and fine-grained keystep recognition -- we outperform SOTA approaches across three datasets (Ego-Exo4D, LEMMA, EPFL-Smart-Kitchen-30). Project page: https://vision.cs.utexas.edu/projects/learning_view_distill/ .