Dual DETRs for Multi-Label Temporal Action Detection

TL;DR

This paper introduces DualDETR, a dual-level query-based framework for multi-label temporal action detection that improves boundary localization by capturing both instance and boundary semantics through a two-branch decoding structure.

Contribution

The paper proposes a novel dual-level query framework with a joint initialization strategy, enhancing temporal boundary detection in multi-label TAD tasks beyond existing methods.

Findings

Achieves superior performance on three multi-label TAD benchmarks.

Significantly improves det-mAP over state-of-the-art methods.

Demonstrates effective boundary localization through dual-level decoding.

Abstract

Temporal Action Detection (TAD) aims to identify the action boundaries and the corresponding category within untrimmed videos. Inspired by the success of DETR in object detection, several methods have adapted the query-based framework to the TAD task. However, these approaches primarily followed DETR to predict actions at the instance level (i.e., identify each action by its center point), leading to sub-optimal boundary localization. To address this issue, we propose a new Dual-level query-based TAD framework, namely DualDETR, to detect actions from both instance-level and boundary-level. Decoding at different levels requires semantics of different granularity, therefore we introduce a two-branch decoding structure. This structure builds distinctive decoding processes for different levels, facilitating explicit capture of temporal cues and semantics at each level. On top of the two-branch design, we present a joint query initialization strategy to align queries from both levels. Specifically, we leverage encoder proposals to match queries from each level in a one-to-one manner. Then, the matched queries are initialized using position and content prior from the matched action proposal. The aligned dual-level queries can refine the matched proposal with complementary cues during subsequent decoding. We evaluate DualDETR on three challenging multi-label TAD benchmarks. The experimental results demonstrate the superior performance of DualDETR to the existing state-of-the-art methods, achieving a substantial improvement under det-mAP and delivering impressive results under seg-mAP.