# SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity

arXiv: https://arxiv.org/abs/2410.20790 · HTML: https://mlsanity.com/paper/2410.20790/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023)
- [Deep Feature Flow for Video Recognition](https://mlsanity.com/paper/1611.07715/) (2016)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video](https://mlsanity.com/paper/1807.06667/) (2018)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)
- [Dynamic Kernel Distillation for Efficient Pose Estimation in Videos](https://mlsanity.com/paper/1908.09216/) (2019)
- [Looking Fast and Slow: Memory-Guided Mobile Video Object Detection](https://mlsanity.com/paper/1903.10172/) (2019)
- [DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos](https://mlsanity.com/paper/2203.03996/) (2022)
- [CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data](https://mlsanity.com/paper/1704.04313/) (2017)
- [Minuet: Accelerating 3D Sparse Convolutions on GPUs](https://mlsanity.com/paper/2401.06145/) (2023)

## Abstract (arXiv)

Deep learning models have become pivotal in the field of video processing and is increasingly critical in practical applications such as autonomous driving and object detection. Although Vision Transformers (ViTs) have demonstrated their power, Convolutional Neural Networks (CNNs) remain a highly efficient and high-performance choice for feature extraction and encoding. However, the intensive computational demands of convolution operations hinder its broader adoption as a video encoder. Given the inherent temporal continuity in video frames, changes between consecutive frames are minimal, allowing for the skipping of redundant computations. This technique, which we term as Diff Computation, presents two primary challenges. First, Diff Computation requires to cache intermediate feature maps to ensure the correctness of non-linear computations, leading to significant memory consumption. Second, the imbalance of sparsity among layers, introduced by Diff Computation, incurs accuracy degradation. To address these issues, we propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation. We integrate these techniques into our framework, SparseTem, to seamlessly support various CNN-based video encoders. SparseTem achieves speedup of 1.79x for EfficientDet and 4.72x for CRNN, with minimal accuracy drop and no additional memory overhead. Extensive experimental results demonstrate that SparseTem sets a new state-of-the-art by effectively utilizing temporal continuity to accelerate CNN-based video encoders.