# DTTNet: Improving Video Shadow Detection via Dark-Aware Guidance and Tokenized Temporal Modeling

arXiv: https://arxiv.org/abs/2511.06925 · HTML: https://mlsanity.com/paper/2511.06925/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks](https://mlsanity.com/paper/2001.06810/) (2020)
- [Rendering Synthetic Objects into Legacy Photographs](https://mlsanity.com/paper/1912.11565/) (2019)
- [Learning to Upsample by Learning to Sample](https://mlsanity.com/paper/2308.15085/) (2023)
- [Revisiting Shadow Detection: A New Benchmark Dataset for Complex World](https://mlsanity.com/paper/1911.06998/) (2019)
- [Triple-cooperative Video Shadow Detection](https://mlsanity.com/paper/2103.06533/) (2021)
- [SCOTCH and SODA: A Transformer Video Shadow Detection Framework](https://mlsanity.com/paper/2211.06885/) (2022)
- [SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels](https://mlsanity.com/paper/2308.12064/) (2023)
- [Detect Any Shadow: Segment Anything for Video Shadow Detection](https://mlsanity.com/paper/2305.16698/) (2023)
- [Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training](https://mlsanity.com/paper/2206.08801/) (2022)
- [SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection](https://mlsanity.com/paper/2308.08935/) (2023)
- [Learning Shadow Correspondence for Video Shadow Detection](https://mlsanity.com/paper/2208.00150/) (2022)
- [Timeline and Boundary Guided Diffusion Network for Video Shadow Detection](https://mlsanity.com/paper/2408.11785/) (2024)
- [Delving into Dark Regions for Robust Shadow Detection](https://mlsanity.com/paper/2402.13631/) (2024)

## Abstract (arXiv)

Video shadow detection confronts two entwined difficulties: distinguishing shadows from complex backgrounds and modeling dynamic shadow deformations under varying illumination. To address shadow-background ambiguity, we leverage linguistic priors through the proposed Vision-language Match Module (VMM) and a Dark-aware Semantic Block (DSB), extracting text-guided features to explicitly differentiate shadows from dark objects. Furthermore, we introduce adaptive mask reweighting to downweight penumbra regions during training and apply edge masks at the final decoder stage for better supervision. For temporal modeling of variable shadow shapes, we propose a Tokenized Temporal Block (TTB) that decouples spatiotemporal learning. TTB summarizes cross-frame shadow semantics into learnable temporal tokens, enabling efficient sequence encoding with minimal computation overhead. Comprehensive Experiments on multiple benchmark datasets demonstrate state-of-the-art accuracy and real-time inference efficiency. Codes are available at https://github.com/city-cheng/DTTNet.