In this work, we study the effect of occlusion on video action recognition.

Compressed videos offer a compelling alternative to raw videos, showing the possibility to significantly reduce the on-line computational and storage cost.

Wethus add more parameters in the head network and see ifthis could close the gap. As UPerNet has anFPN-likehead network, we 1 add parameters by replacing FPN with BiFPN. Fromthisfigure,wecan observethat the features across heads inthe Transformer decoder are almost the same. Semantic Segmentation on ADE20KFor the semantic segmentation task, we adopt widelyused ADE20K [11] as the benchmark. Table 7: Hyperparameters for the frozen setting and full finetuning on Kinetics-400 video action recognition.

This paper presents OmniVL, a new foundation model to support both imagelanguage and video-language tasks using one universal architecture.

Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input. Our proposed bottleneck cross-attention mechanism enables the spatial and temporal expert models to exchange information and make synergistic predictions, leading to improved performance. We validate the proposed method with extensive experiments on public benchmarks with different characteristics: EPIC-Kitchens-100, Something-Something-V2, and Kinetics-400. Our method consistently shows favorable performance across these datasets, while the performance of existing methods fluctuates depending on the dataset characteristics. The code is available at https://github.com/KHU-VLL/CAST.

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more efficient in computation, the latter often obtains better performance. In this paper, we attribute this to a dilemma between the sufficiency and the efficiency of interactions among various positions in different frames. These interactions affect the extraction of task-relevant information shared among frames. To resolve this issue, we prove that frame-by-frame alignments have the potential to increase the mutual information between frame representations, thereby including more task-relevant information to boost effectiveness. Then we propose Alignment-guided Temporal Attention (ATA) to extend 1-dimensional temporal attention with parameter-free patch-level alignments between neighboring frames. It can act as a general plug-in for image backbones to conduct the action recognition task without any model-specific design. Extensive experiments on multiple benchmarks demonstrate the superiority and generality of our module.

Convolutional Neural Networks (CNNs) have been the dominant model for video action recognition. Due to the huge memory and compute demand, popular action recognition networks need to be trained with small batch sizes, which makes learning discriminative spatial-temporal representations for videos become a challenging problem. In this paper, we present Dynamic Normalization and Relay (DNR), an improved normalization design, to augment the spatial-temporal representation learning of any deep action recognition model, adapting to small batch size training settings. We observe that state-of-the-art action recognition networks usually apply the same normalization parameters to all video data, and ignore the dependencies of the estimated normalization parameters between neighboring frames (at the same layer) and between neighboring layers (with all frames of a video clip). Inspired by this, DNR introduces two dynamic normalization relay modules to explore the potentials of cross-temporal and cross-layer feature distribution dependencies for estimating accurate layer-wise normalization parameters. These two DNR modules are instantiated as a light-weight recurrent structure conditioned on the current input features, and the normalization parameters estimated from the neighboring frames based features at the same layer or from the whole video clip based features at the preceding layers. We first plug DNR into prevailing 2D CNN backbones and test its performance on public action recognition datasets including Kinetics and Something-Something. Experimental results show that DNR brings large performance improvements to the baselines, achieving over 4.4% absolute margins in top-1 accuracy without training bells and whistles.