# TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning

arXiv: https://arxiv.org/abs/2203.05928 · HTML: https://mlsanity.com/paper/2203.05928/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Beyond Short Snippets: Deep Networks for Video Classification](https://mlsanity.com/paper/1503.08909/) (2015)
- [Distractor-aware Siamese Networks for Visual Object Tracking](https://mlsanity.com/paper/1808.06048/) (2018)
- [TDN: Temporal Difference Networks for Efficient Action Recognition](https://mlsanity.com/paper/2012.10071/) (2020)
- [CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning](https://mlsanity.com/paper/1910.04744/) (2019)
- [Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks](https://mlsanity.com/paper/1912.09930/) (2019)
- [Video Modeling with Correlation Networks](https://mlsanity.com/paper/1906.03349/) (2019)
- [Temporal Query Networks for Fine-grained Video Understanding](https://mlsanity.com/paper/2104.09496/) (2021)
- [Appearance-and-Relation Networks for Video Classification](https://mlsanity.com/paper/1711.09125/) (2017)
- [Compact Generalized Non-local Network](https://mlsanity.com/paper/1810.13125/) (2018)
- [V4D:4D Convolutional Neural Networks for Video-level Representation Learning](https://mlsanity.com/paper/2002.07442/) (2020)
- [Learning Object Permanence from Video](https://mlsanity.com/paper/2003.10469/) (2020)
- [Hopper: Multi-hop Transformer for Spatiotemporal Reasoning](https://mlsanity.com/paper/2103.10574/) (2021)

## Built on by (most cited first, 12 of 12)

- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)
- [Learning What and Where: Disentangling Location and Identity Tracking Without Supervision](https://mlsanity.com/paper/2205.13349/) (2022)
- [An Empirical Study of Autoregressive Pre-training from Videos](https://mlsanity.com/paper/2501.05453/) (2025)
- [Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition](https://mlsanity.com/paper/2307.06947/) (2023)
- [Look, Remember and Reason: Grounded reasoning in videos with language models](https://mlsanity.com/paper/2306.17778/) (2023)
- [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023)
- [Benchmarks for Physical Reasoning AI](https://mlsanity.com/paper/2312.10728/) (2023)
- [CDST: Color Disentangled Style Transfer for Universal Style Reference Customization](https://mlsanity.com/paper/2506.13770/) (2025)
- [PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition](https://mlsanity.com/paper/2407.02934/) (2024)
- [Hyper-parameter tuning for text guided image editing](https://mlsanity.com/paper/2407.21703/) (2024)
- [Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning](https://mlsanity.com/paper/2606.14746/) (2026)
- [TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillation](https://mlsanity.com/paper/2606.20709/) (2026)

## Abstract (arXiv)

Temporal Reasoning is one important functionality for vision intelligence. In computer vision research community, temporal reasoning is usually studied in the form of video classification, for which many state-of-the-art Neural Network structures and dataset benchmarks are proposed in recent years, especially 3D CNNs and Kinetics. However, some recent works found that current video classification benchmarks contain strong biases towards static features, thus cannot accurately reflect the temporal modeling ability. New video classification benchmarks aiming to eliminate static biases are proposed, with experiments on these new benchmarks showing that the current clip-based 3D CNNs are outperformed by RNN structures and recent video transformers. In this paper, we find that 3D CNNs and their efficient depthwise variants, when video-level sampling strategy is used, are actually able to beat RNNs and recent vision transformers by significant margins on static-unbiased temporal reasoning benchmarks. Further, we propose Temporal Fully Connected Block (TFC Block), an efficient and effective component, which approximates fully connected layers along temporal dimension to obtain video-level receptive field, enhancing the spatiotemporal reasoning ability. With TFC blocks inserted into Video-level 3D CNNs (V3D), our proposed TFCNets establish new state-of-the-art results on synthetic temporal reasoning benchmark, CATER, and real world static-unbiased dataset, Diving48, surpassing all previous methods.