# Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks

arXiv: https://arxiv.org/abs/2211.06023 · HTML: https://mlsanity.com/paper/2211.06023/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 30 of 35)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [G-TAD: Sub-Graph Localization for Temporal Action Detection](https://mlsanity.com/paper/1911.11462/) (2019)
- [The THUMOS Challenge on Action Recognition for Videos "in the Wild"](https://mlsanity.com/paper/1604.06182/) (2016)
- [Graph Convolutional Networks for Temporal Action Localization](https://mlsanity.com/paper/1909.03252/) (2019)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [Local-Global Video-Text Interactions for Temporal Grounding](https://mlsanity.com/paper/2004.07514/) (2020)
- [Towards Long-Form Video Understanding](https://mlsanity.com/paper/2106.11310/) (2021)
- [Fast Learning of Temporal Action Proposal via Dense Boundary Generator](https://mlsanity.com/paper/1911.04127/) (2019)
- [Boundary Proposal Network for Two-Stage Natural Language Video Localization](https://mlsanity.com/paper/2103.08109/) (2021)
- [TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks](https://mlsanity.com/paper/2011.11479/) (2020)
- [CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning](https://mlsanity.com/paper/2103.16392/) (2021)
- [Counting Out Time: Class Agnostic Video Repetition Counting in the Wild](https://mlsanity.com/paper/2006.15418/) (2020)
- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)
- [SF-Net: Single-Frame Supervision for Temporal Action Localization](https://mlsanity.com/paper/2003.06845/) (2020)
- [Boundary-sensitive Pre-training for Temporal Localization in Videos](https://mlsanity.com/paper/2011.10830/) (2020)
- [An Empirical Study of End-to-End Temporal Action Detection](https://mlsanity.com/paper/2204.02932/) (2022)
- [Revisiting the Transferability of Supervised Pretraining: an MLP Perspective](https://mlsanity.com/paper/2112.00496/) (2021)
- [Unsupervised Pre-training for Temporal Action Localization Tasks](https://mlsanity.com/paper/2203.13609/) (2022)
- [Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/2012.02646/) (2020)

## Built on by (most cited first, 5 of 5)

- [Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization](https://mlsanity.com/paper/2409.07967/) (2024)
- [HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization](https://mlsanity.com/paper/2408.06437/) (2024)
- [Online Generic Event Boundary Detection](https://mlsanity.com/paper/2510.06855/) (2025)
- [Long-term Pre-training for Temporal Action Detection with Transformers](https://mlsanity.com/paper/2408.13152/) (2024)
- [Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition](https://mlsanity.com/paper/2311.17118/) (2023)

## Abstract (arXiv)

Temporal Action Localization (TAL) methods typically operate on top of feature sequences from a frozen snippet encoder that is pretrained with the Trimmed Action Classification (TAC) tasks, resulting in a task discrepancy problem. While existing TAL methods mitigate this issue either by retraining the encoder with a pretext task or by end-to-end fine-tuning, they commonly require an overload of high memory and computation. In this work, we introduce Soft-Landing (SoLa) strategy, an efficient yet effective framework to bridge the transferability gap between the pretrained encoder and the downstream tasks by incorporating a light-weight neural network, i.e., a SoLa module, on top of the frozen encoder. We also propose an unsupervised training scheme for the SoLa module; it learns with inter-frame Similarity Matching that uses the frame interval as its supervisory signal, eliminating the need for temporal annotations. Experimental evaluation on various benchmarks for downstream TAL tasks shows that our method effectively alleviates the task discrepancy problem with remarkable computational efficiency.