We don't Need Thousand Proposals$\colon$ Single Shot Actor-Action Detection in Videos

TL;DR

SSA2D is a novel end-to-end deep network for actor-action detection in videos that operates without proposals, enabling scalable, fast, and memory-efficient detection of multiple actors and actions at pixel level.

Contribution

The paper introduces SSA2D, a fully convolutional, single-shot network that eliminates the need for region proposals, improving scalability and efficiency in dense video scenes.

Findings

SSA2D is 11x faster during inference.

It achieves comparable or better performance than prior methods.

Requires fewer network parameters.

Abstract

We propose SSA2D, a simple yet effective end-to-end deep network for actor-action detection in videos. The existing methods take a top-down approach based on region-proposals (RPN), where the action is estimated based on the detected proposals followed by post-processing such as non-maximal suppression. While effective in terms of performance, these methods pose limitations in scalability for dense video scenes with a high memory requirement for thousands of proposals. We propose to solve this problem from a different perspective where we don't need any proposals. SSA2D is a unified network, which performs pixel level joint actor-action detection in a single-shot, where every pixel of the detected actor is assigned an action label. SSA2D has two main advantages: 1) It is a fully convolutional network which does not require any proposals and post-processing making it memory as well as time efficient, 2) It is easily scalable to dense video scenes as its memory requirement is independent of the number of actors present in the scene. We evaluate the proposed method on the Actor-Action dataset (A2D) and Video Object Relation (VidOR) dataset, demonstrating its effectiveness in multiple actors and action detection in a video. SSA2D is 11x faster during inference with comparable (sometimes better) performance and fewer network parameters when compared with the prior works.