# Unsupervised Object Discovery and Tracking in Video Collections

arXiv: https://arxiv.org/abs/1505.03825 · HTML: https://mlsanity.com/paper/1505.03825/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2015.

## Built on by (most cited first, 17 of 17)

- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Convolutional Hough Matching Networks](https://mlsanity.com/paper/2103.16831/) (2021)
- [TAPNext: Tracking Any Point (TAP) as Next Token Prediction](https://mlsanity.com/paper/2504.05579/) (2025)
- [MOST: Multiple Object localization with Self-supervised Transformers for object discovery](https://mlsanity.com/paper/2304.05387/) (2023)
- [The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory](https://mlsanity.com/paper/2105.01652/) (2021)
- [Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence](https://mlsanity.com/paper/2109.05221/) (2021)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [Learning to Discover and Detect Objects](https://mlsanity.com/paper/2210.10774/) (2022)
- [Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression](https://mlsanity.com/paper/2111.09204/) (2021)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)
- [Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video](https://mlsanity.com/paper/2407.15794/) (2024)
- [The Background Also Matters: Background-Aware Motion-Guided Objects Discovery](https://mlsanity.com/paper/2311.02633/) (2023)
- [Tunable Hybrid Proposal Networks for the Open World](https://mlsanity.com/paper/2208.11050/) (2022)
- [MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos](https://mlsanity.com/paper/2405.14841/) (2024)
- [Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos](https://mlsanity.com/paper/2407.06018/) (2024)
- [Weakly-Supervised Action Detection Guided by Audio Narration](https://mlsanity.com/paper/2205.05895/) (2022)
- [Real-time Unsupervised Object Discovery from Asynchronous Event Streams](https://mlsanity.com/paper/2608.26644/) (2026)

## Abstract (arXiv)

This paper addresses the problem of automatically localizing dominant objects as spatio-temporal tubes in a noisy collection of videos with minimal or even no supervision. We formulate the problem as a combination of two complementary processes: discovery and tracking. The first one establishes correspondences between prominent regions across videos, and the second one associates successive similar object regions within the same video. Interestingly, our algorithm also discovers the implicit topology of frames associated with instances of the same object class across different videos, a role normally left to supervisory information in the form of class labels in conventional image and video understanding methods. Indeed, as demonstrated by our experiments, our method can handle video collections featuring multiple object classes, and substantially outperforms the state of the art in colocalization, even though it tackles a broader problem with much less supervision.