Long-tailed Video Recognition

深度学习（DL）的兴起和公共大规模视觉数据集（如ImageNet [1]）的可用性导致了现代计算机视觉的重大进展。然而，知识转移的DL模型从公共数据集到真实的世界的用例面临着多重挑战，由于问题，如域的差异，数据稀缺等两个最重要的挑战是：DL模型在公共数据集上训练给新的环境或领域的次优性能。由于某些领域的长尾性质，从头开始重新训练DL模型或在新领域中对其进行微调仍然可能提供次优和有偏差的性能。这些缺点激起了强烈的研究动机，并分别被称为“领域适应”和“长尾识别”问题。尽管在这些领域已经有了各种各样的工作，但大多数都涉及基于图像的问题。然而，上述缺点也出现在视频识别中，并且很少被探索。

The rise of deep learning (DL) and the availability of publiclarge-scale vision datasets such as ImageNet [1] have led to significant progress inmodern day computer vision. However, knowledge transfer of DL models frompublic datasets to real world usecases faces multiple challenges due to issuessuch as differences in domains, data scarcity etc. Two of the most significantchallenges are :DL models trained on public datasets give suboptimal performance in novel environments or domains. Therefore they either need to be retrained from scratch or fine-tuned for each domain.Re-training DL models from scratch or fine-tuning them in novel domains may still provide sub-optimal and biased performance due to long-tailed nature of some domains.These shortcomings have stirred up strong research motivations and are popularly known as problems of 'domain adaptation' and 'long-tailed recognition' respectively. Even though there have been various works in these fields, most of them concern with image-based problems. However, the above shortcomings appear in video recognition as well and have been scarcely explored.