# Closing the Estimation Gap: Training-Free Transductive Inference for Cross-Domain Few-Shot Action Recognition

arXiv: https://arxiv.org/abs/2610.18209 · HTML: https://mlsanity.com/paper/2610.18209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)
- [Prototype Rectification for Few-Shot Learning](https://mlsanity.com/paper/1911.10713/) (2019)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)
- [Embedding Propagation: Smoother Manifold for Few-Shot Classification](https://mlsanity.com/paper/2003.04151/) (2020)
- [Self-training for Few-shot Transfer Across Extreme Task Differences](https://mlsanity.com/paper/2010.07734/) (2020)
- [Leveraging the Feature Distribution in Transfer-based Few-Shot Learning](https://mlsanity.com/paper/2006.03806/) (2020)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data](https://mlsanity.com/paper/2106.07807/) (2021)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments](https://mlsanity.com/paper/2207.10785/) (2022)
- [CDFSL-V: Cross-Domain Few-Shot Learning for Videos](https://mlsanity.com/paper/2309.03989/) (2023)
- [DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition](https://mlsanity.com/paper/2407.05657/) (2024)
- [TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition](https://mlsanity.com/paper/2411.19041/) (2024)
- [TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification](https://mlsanity.com/paper/2106.11173/) (2021)
- [Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition](https://mlsanity.com/paper/2610.00064/) (2026)

## Abstract (arXiv)

Cross-domain few-shot action recognition (CD-FSAR) aims to recognise unseen action classes in a target domain from a handful of labelled videos. Despite advances in representation learning, CD-FSAR inference still relies on prototypes estimated from extremely limited support examples. To assess this bottleneck, we perform an oracle analysis with the representation fixed. Constructing oracle prototypes and decision boundaries from ground-truth query labels improves 5-way 1-shot accuracy by 7--20 percentage points across five target datasets. This reveals a substantial estimation gap: the representation contains useful discriminative information, but prototypes and boundaries estimated from scarce supports fail to capture each episode's true class structure. Motivated by this, we propose TRACE, a training-free transductive inference framework that improves episode-level estimation without modifying the backbone. TRACE comprises two complementary stages. Confidence-Thresholded Transductive Prototype Refinement (CTPR) refines support-based prototypes using confidently predicted queries. The refined prototypes initialise a lightweight per-episode classifier, which Transductive Classifier Refinement (TCR) further adapts by encouraging confident, class-balanced predictions over all queries. Together, the two stages improve prototype and boundary estimation, enabling better use of information in the unlabelled queries. Across five target datasets (HMDB51, UCF101, SSv2, Diving48, and RareAct) in both 1-shot and 5-shot settings, TRACE consistently improves a strong CD-FSAR baseline, including gains of more than six percentage points on HMDB51 1-shot, while recovering much of the oracle-estimated gap. These results suggest that improving test-time estimation is a powerful, broadly applicable complement to representation learning for CD-FSAR under extreme support scarcity.