# Exploiting Temporal Information for DCNN-based Fine-Grained Object Classification

arXiv: https://arxiv.org/abs/1608.00486 · HTML: https://mlsanity.com/paper/1608.00486/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2016.

## Built on by (most cited first, 7 of 7)

- [Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset](https://mlsanity.com/paper/2207.10664/) (2022)
- [Knowledge Mining with Scene Text for Fine-Grained Recognition](https://mlsanity.com/paper/2203.14215/) (2022)
- [The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment](https://mlsanity.com/paper/2511.21331/) (2025)
- [AirBirds: A Large-scale Challenging Dataset for Bird Strike Prevention in Real-world Airports](https://mlsanity.com/paper/2304.11662/) (2023)
- [It's a Matter of Time: Three Lessons on Long-Term Motion for Perception](https://mlsanity.com/paper/2602.14705/) (2026)
- [Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning](https://mlsanity.com/paper/2509.06306/) (2025)
- [Not All Birds Look The Same: Identity-Preserving Generation For Birds](https://mlsanity.com/paper/2512.04485/) (2025)

## Abstract (arXiv)

Fine-grained classification is a relatively new field that has concentrated on using information from a single image, while ignoring the enormous potential of using video data to improve classification. In this work we present the novel task of video-based fine-grained object classification, propose a corresponding new video dataset, and perform a systematic study of several recent deep convolutional neural network (DCNN) based approaches, which we specifically adapt to the task. We evaluate three-dimensional DCNNs, two-stream DCNNs, and bilinear DCNNs. Two forms of the two-stream approach are used, where spatial and temporal data from two independent DCNNs are fused either via early fusion (combination of the fully-connected layers) and late fusion (concatenation of the softmax outputs of the DCNNs). For bilinear DCNNs, information from the convolutional layers of the spatial and temporal DCNNs is combined via local co-occurrences. We then fuse the bilinear DCNN and early fusion of the two-stream approach to combine the spatial and temporal information at the local and global level (Spatio-Temporal Co-occurrence). Using the new and challenging video dataset of birds, classification performance is improved from 23.1% (using single images) to 41.1% when using the Spatio-Temporal Co-occurrence system. Incorporating automatically detected bounding box location further improves the classification accuracy to 53.6%.