# whu-nercms at trecvid2021:instance search task

arXiv: https://arxiv.org/abs/2111.00228 · HTML: https://mlsanity.com/paper/2111.00228/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 30 Oct 2021.

## Builds on (most cited first, 8 of 8)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information](https://mlsanity.com/paper/2103.05399/) (2021)
- [PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection](https://mlsanity.com/paper/1912.12898/) (2019)
- [Reformulating HOI Detection as Adaptive Set Prediction](https://mlsanity.com/paper/2103.05983/) (2021)
- [TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device](https://mlsanity.com/paper/2109.13227/) (2021)
- [Actor Conditioned Attention Maps for Video Action Detection](https://mlsanity.com/paper/1812.11631/) (2018)

## Abstract (arXiv)

We will make a brief introduction of the experimental methods and results of the WHU-NERCMS in the TRECVID2021 in the paper. This year we participate in the automatic and interactive tasks of Instance Search (INS). For the automatic task, the retrieval target is divided into two parts, person retrieval, and action retrieval. We adopt a two-stage method including face detection and face recognition for person retrieval and two kinds of action detection methods consisting of three frame-based human-object interaction detection methods and two video-based general action detection methods for action retrieval. After that, the person retrieval results and action retrieval results are fused to initialize the result ranking lists. In addition, we make attempts to use complementary methods to further improve search performance. For interactive tasks, we test two different interaction strategies on the fusion results. We submit 4 runs for automatic and interactive tasks respectively. The introduction of each run is shown in Table 1. The official evaluations show that the proposed strategies rank 1st in both automatic and interactive tracks.