# A Discriminative CNN Video Representation for Event Detection

arXiv: https://arxiv.org/abs/1411.4006 · HTML: https://mlsanity.com/paper/1411.4006/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2014.

## Built on by (most cited first, 20 of 20)

- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval](https://mlsanity.com/paper/2104.10054/) (2021)
- [Learning To Recognize Procedural Activities with Distant Supervision](https://mlsanity.com/paper/2201.10990/) (2022)
- [Learning and Verification of Task Structure in Instructional Videos](https://mlsanity.com/paper/2303.13519/) (2023)
- [SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition](https://mlsanity.com/paper/2308.04369/) (2023)
- [Self-Conditioned Probabilistic Learning of Video Rescaling](https://mlsanity.com/paper/2107.11639/) (2021)
- [Towards Neuro-Symbolic Video Understanding](https://mlsanity.com/paper/2403.11021/) (2024)
- [UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist](https://mlsanity.com/paper/2511.08521/) (2025)
- [Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition](https://mlsanity.com/paper/2101.06636/) (2021)
- [We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback](https://mlsanity.com/paper/2504.17180/) (2025)
- [Video-based Human Action Recognition using Deep Learning: A Review](https://mlsanity.com/paper/2208.03775/) (2022)
- [Video Recognition in Portrait Mode](https://mlsanity.com/paper/2312.13746/) (2023)
- [A Challenge to Build Neuro-Symbolic Video Agents](https://mlsanity.com/paper/2505.13851/) (2025)
- [Decompose the Sounds and Pixels, Recompose the Events](https://mlsanity.com/paper/2112.11547/) (2021)
- [Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning](https://mlsanity.com/paper/2209.00990/) (2022)
- [Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning](https://mlsanity.com/paper/2105.04143/) (2021)
- [ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction](https://mlsanity.com/paper/2511.18701/) (2025)
- [Unconstrained Face Recognition using ASURF and Cloud-Forest Classifier optimized with VLAD](https://mlsanity.com/paper/2104.00842/) (2021)
- [Video Imprint](https://mlsanity.com/paper/2106.03283/) (2021)
- [Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding](https://mlsanity.com/paper/2110.08063/) (2021)

## Abstract (arXiv)

In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. The focus of this paper is to effectively leverage deep Convolutional Neural Networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkit. This paper makes two contributions to the inference of CNN video representation. First, while average pooling and max pooling have long been the standard approaches to aggregating frame level static features, we show that performance can be significantly improved by taking advantage of an appropriate encoding method. Second, we propose using a set of latent concept descriptors as the frame descriptor, which enriches visual information while keeping it computationally affordable. The integration of the two contributions results in a new state-of-the-art performance in event detection over the largest video datasets. Compared to improved Dense Trajectories, which has been recognized as the best video representation for event detection, our new representation improves the Mean Average Precision (mAP) from 27.6% to 36.8% for the TRECVID MEDTest 14 dataset and from 34.0% to 44.6% for the TRECVID MEDTest 13 dataset. This work is the core part of the winning solution of our CMU-Informedia team in TRECVID MED 2014 competition.