MMViT: Bridging Mamba and Attention for efficient video action recognition in sports.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition

Real-time human action recognition on Internet-of-Things (IoT) edge devices requires models that capture rich spatio-temporal cues within strict latency, memory, and power envelopes. Current 3D CNNs, video transformers, and shift-based ViT deliver high accuracy but come at computational costs that preclude edge IoT deployment. This paper proposes CoDAT, a Collaborative Dual-Attention Transformer that replaces conventional multi-head attention with a lightweight dual-branch module: Spatial Convolutional Attention (SCA) for local aggregation and Strided Single-Head Attention (SSHA) for global context. SSHA jointly compresses the spatial resolution and channel dimensions of the query, key, and value tensors via stride-based sparse projection, then fuses the resulting global and local features at a markedly reduced cost. To enable temporal communication across frames, a parameter-free TShift module is embedded in each block. Extensive experiments on Jetson AGX Orin and Raspberry Pi 5 demonstrate that CoDAT achieves an energy-accuracy balance in both image and action recognition. On ImageNet-1K, CoDAT-M runs 2x faster than EfficientViT384 and FastViT-S12 at comparable accuracy, and CoDAT-L matches ViT-S with 3x fewer parameters at 2x higher throughput. On Kinetics-400 and MA-52, CoDAT achieves competitive Top-1 accuracy against state-of-the-art CNN, transformer, and hybrid baselines while running up to 2.9x faster than VSwin-T, 2x faster than ViT-Temporal-Shift variants, and 5x faster than UniFormer-B. On UCF-101, CoDAT-S384 matches TokShift and LAPS while being 6x faster and requiring up to 13x fewer FLOPs, establishing an efficiency-accuracy balance for real-time action recognition in edge IoT perception systems. Code is available at https://github.com/novendrastywn/CoDAT .

Convolutional Network with Mamba State Space Models for Skeleton-based Action Recognition

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding

It is proved that the computationally cheaper split space-time attention is equivalent to full space-time attention and is promising to extend VideoSEMA to longer videos with a dilated/sparse temporal attention.

Deep Features Evaluation Method of Human Action Recognition Based on Convolutional Neural Network

A compact and deployable Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) framework that combines a 2D convolutional backbone (AlexNet) for frame-level descriptors with an LSTM head for sequence modeling is proposed, indicating a robust, real-time-capable solution for video understanding in both offline analytics and online deployment.

AVT-PAC: A Pipeline for Multimodal Action Prediction and Captioning

Action prediction from frames and videos is a well-studied problem. Models trained with a single modality, mostly vision, will fail in low-light conditions. Recent works have attempted to predict action categories using vision-language and audio-visual models. A challenge, however, is that some dataset annotations lack temporal ground truth and include only the vision modality. Relying on transformers and an intelligent Vision Language Model (VLM) is a viable solution, but deploying them on edge devices could lead to reduced performance and hallucinations. This work presents an Audio-Visual-Text (AVT)-based multi-step Pipeline for Action Prediction and Captioning (AVT-PAC) to address this problem. First, for an input video, we identify the area to focus on using the Region-of-Interest (ROI) Extraction module. CLIP and CLAP encoders are used for ROI prediction. However, the ROI extracted region may vary in duration, resulting in a large number of frames to be processed. To avoid learning from redundant frames, we uniformly sample key frames within the ROI extracted region using a keyframe extraction module. These keyframes are then used to train an Audio-Visual Action and Text-Aware Representation (AVATAR) model to predict actions and captions. Through systematic experiments, we demonstrated that the proposed AVATAR-TCN model beats the present state-of-the-art (SOTA) baselines on the AVE dataset. Code is available in https://github.com/Ifovia/AVT-PAC

ActionLMM: captioning long-video actions with memory-augmented VLMs

This work introduces ActionLMM, a memory-augmented vision-language model for long-video action summarization that aligns visual and motion modalities through joint representation learning and leverages a novel dual-memory mechanism to retain both local motion details and global temporal structure.