# CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos

arXiv: https://arxiv.org/abs/2303.09044 · HTML: https://mlsanity.com/paper/2303.09044/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 120 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 30 of 62)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization](https://mlsanity.com/paper/1704.04232/) (2017)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [Multiple Object Tracking: A Literature Review](https://mlsanity.com/paper/1409.7618/) (2014)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)
- [Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs](https://mlsanity.com/paper/2008.02312/) (2020)
- [Memory Enhanced Global-Local Aggregation for Video Object Detection](https://mlsanity.com/paper/2003.12063/) (2020)
- [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models](https://mlsanity.com/paper/1908.01224/) (2019)
- [CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2212.09506/) (2022)

## Built on by (most cited first, 7 of 7)

- [Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues](https://mlsanity.com/paper/2402.00281/) (2024)
- [DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2310.06196/) (2023)
- [EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic Surgery](https://mlsanity.com/paper/2509.15596/) (2025)
- [Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos](https://mlsanity.com/paper/2407.06018/) (2024)
- [TeD-Loc: Text Distillation for Weakly Supervised Object Localization](https://mlsanity.com/paper/2501.12632/) (2025)
- [PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization](https://mlsanity.com/paper/2503.24135/) (2025)
- [Temporal-consistent CAMs for Weakly Supervised Video Segmentation in Waste Sorting](https://mlsanity.com/paper/2502.01455/) (2025)

## Abstract (arXiv)

Leveraging spatiotemporal information in videos is critical for weakly supervised video object localization (WSVOL) tasks. However, state-of-the-art methods only rely on visual and motion cues, while discarding discriminative information, making them susceptible to inaccurate localizations. Recently, discriminative models have been explored for WSVOL tasks using a temporal class activation mapping (CAM) method. Although their results are promising, objects are assumed to have limited movement from frame to frame, leading to degradation in performance for relatively long-term dependencies. This paper proposes a novel CAM method for WSVOL that exploits spatiotemporal information in activation maps during training without constraining an object's position. Its training relies on Co-Localization, hence, the name CoLo-CAM. Given a sequence of frames, localization is jointly learned based on color cues extracted across the corresponding maps, by assuming that an object has similar color in consecutive frames. CAM activations are constrained to respond similarly over pixels with similar colors, achieving co-localization. This improves localization performance because the joint learning creates direct communication among pixels across all image locations and over all frames, allowing for transfer, aggregation, and correction of localizations. Co-localization is integrated into training by minimizing the color term of a conditional random field (CRF) loss over a sequence of frames/CAMs. Extensive experiments on two challenging YouTube-Objects datasets of unconstrained videos show the merits of our method, and its robustness to long-term dependencies, leading to new state-of-the-art performance for WSVOL task.