No Arabic abstract
In this work we present a new efficient approach to Human Action Recognition called Video Transformer Network (VTN). It leverages the latest advances in Computer Vision and Natural Language Processing and applies them to video understanding. The proposed method allows us to create lightweight CNN models that achieve high accuracy and real-time speed using just an RGB mono camera and general purpose CPU. Furthermore, we explain how to improve accuracy by distilling from multiple models with different modalities into a single model. We conduct a comparison with state-of-the-art methods and show that our approach performs on par with most of them on famous Action Recognition datasets. We benchmark the inference time of the models using the modern inference framework and argue that our approach compares favorably with other methods in terms of speed/accuracy trade-off, running at 56 FPS on CPU. The models and the training code are available.
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill this gap and investigate the use of transformers for efficient action recognition. We propose a novel, lightweight action recognition architecture, VideoLightFormer. In a factorized fashion, we carefully extend the 2D convolutional Temporal Segment Network with transformers, while maintaining spatial and temporal video structure throughout the entire model. Existing methods often resort to one of the two extremes, where they either apply huge transformers to video features, or minimal transformers on highly pooled video features. Our method differs from them by keeping the transformer models small, but leveraging full spatiotemporal feature structure. We evaluate VideoLightFormer in a high-efficiency setting on the temporally-demanding EPIC-KITCHENS-100 and Something-Something-V2 (SSV2) datasets and find that it achieves a better mix of efficiency and accuracy than existing state-of-the-art models, apart from the Temporal Shift Module on SSV2.
Growing amount of different practical tasks in a video understanding problem has addressed the great challenge aiming to design an universal solution, which should be available for broad masses and suitable for the demanding edge-oriented inference. In this paper we are focused on designing a network architecture and a training pipeline to tackle the mentioned challenges. Our architecture takes the best from the previous ones and brings the ability to be successful not only in appearance-based action recognition tasks but in motion-based problems too. Furthermore, the induced label noise problem is formulated and Adaptive Clip Selection (ACS) framework is proposed to deal with it. Together it makes the LIGAR framework the general-purpose action recognition solution. We also have reported the extensive analysis on the general and gesture datasets to show the excellent trade-off between the performance and the accuracy in comparison to the state-of-the-art solutions. Training code is available at: https://github.com/openvinotoolkit/training_extensions. For the efficient edge-oriented inference all trained models can be exported into the OpenVINO format.
Convolutional Architecture for Fast Feature Encoding (CAFFE) [11] is a software package for the training, classifying, and feature extraction of images. The UCF Sports Action dataset is a widely used machine learning dataset that has 200 videos taken in 720x480 resolution of 9 different sporting activities: diving, golf, swinging, kicking, lifting, horseback riding, running, skateboarding, swinging (various gymnastics), and walking. In this report we report on a caffe feature extraction pipeline of images taken from the videos of the UCF Sports Action dataset. A similar test was performed on overfeat, and results were inferior to caffe. This study is intended to explore the architecture and hyper parameters needed for effective static analysis of action in videos and classification over a variety of image datasets.
Spatiotemporal action localization requires the incorporation of two sources of information into the designed architecture: (1) temporal information from the previous frames and (2) spatial information from the key frame. Current state-of-the-art approaches usually extract these information with separate networks and use an extra mechanism for fusion to get detections. In this work, we present YOWO, a unified CNN architecture for real-time spatiotemporal action localization in video streams. YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation. Since the whole architecture is unified, it can be optimized end-to-end. The YOWO architecture is fast providing 34 frames-per-second on 16-frames input clips and 62 frames-per-second on 8-frames input clips, which is currently the fastest state-of-the-art architecture on spatiotemporal action localization task. Remarkably, YOWO outperforms the previous state-of-the art results on J-HMDB-21 and UCF101-24 with an impressive improvement of ~3% and ~12%, respectively. We make our code and pretrained models publicly available.
Deep neural networks have rapidly become the mainstream method for face recognition. However, deploying such models that contain an extremely large number of parameters to embedded devices or in application scenarios with limited memory footprint is challenging. In this work, we present an extremely lightweight and accurate face recognition solution. We utilize neural architecture search to develop a new family of face recognition models, namely PocketNet. We also propose to enhance the verification performance of the compact model by presenting a novel training paradigm based on knowledge distillation, namely the multi-step knowledge distillation. We present an extensive experimental evaluation and comparisons with the recent compact face recognition models on nine different benchmarks including large-scale evaluation benchmarks such as IJB-B, IJB-C, and MegaFace. PocketNets have consistently advanced the state-of-the-art (SOTA) face recognition performance on nine mainstream benchmarks when considering the same level of model compactness. With 0.92M parameters, our smallest network PocketNetS-128 achieved very competitive results to recent SOTA compacted models that contain more than 4M parameters. Training codes and pre-trained models are publicly released https://github.com/fdbtrs/PocketNet.