paper-with-me

홈 › Papers

Evolving Losses for Unlabeled Video Representation Learning

2019-06-07 · AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo

We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly used for a new task such as zero/few-shot learning. We formulate our unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are also shared across different modalities via distillation. Further, we also introduce the concept of finding a better loss function to train such multi-task multi-modal representation space using an evolutionary algorithm; our method automatically searches over different combinations of loss functions capturing multiple (self-supervised) tasks and modalities. Our formulation allows for the distillation of audio, optical flow and temporal information into a single, RGB-based convolutional neural network. We also compare the effects of using additional unlabeled video data and evaluate our representation learning on standard public video datasets.

📄 PDF Abstract BibTeX arXiv:1906.03248

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningMulti-Task LearningOptical Flow EstimationRepresentation Learning

Similar Papers 제목 키워드 기반

Evolving Losses for Unsupervised Video Representation Learning

2020-02-26 · CVPR 2020 6 · AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo

We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and ze…

Action RecognitionFew-Shot LearningMulti-Task LearningRepresentation Learning+1

ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations

2024-01-01 · CVPR 2024 1 · Yuanhang Zhang, Shuang Yang, Shiguang Shan, Xilin Chen

We propose a novel strategy ES3 for self-supervised learning of robust audio-visual speech representations from unlabeled talking face videos. While many recent approaches for this task primarily rely on guiding the …

Audio-Visual Speech RecognitionLipreadingSelf-Supervised LearningSpeech Recognition

Spatial-then-Temporal Self-Supervised Learning for Video Correspondence

2022-09-16 · CVPR 2023 1 · Rui Li, Dong Liu

In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or video…

Contrastive LearningSelf-Supervised Learning

Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification

2020-07-21 · ECCV 2020 8 · Dripta S. Raychaudhuri, Amit K. Roy-Chowdhury

While supervised techniques in re-identification are extremely effective, the need for large amounts of annotations makes them impractical for large camera networks. One-shot re-identification, which uses a singular labe…

One-Shot Learning

Semi-Supervised Learning for Video Captioning

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Ke Lin, Zhuoxin Gan, LiWei Wang

Deep neural networks have made great success on video captioning in supervised learning setting. However, annotating videos with descriptions is very expensive and time-consuming. If the video captioning algorithm can be…

Video Captioning