VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

• URL: http://arxiv.org/abs/2410.03478v1
• Date: Fri, 4 Oct 2024 14:52:09 GMT
• Title: VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
• Authors: Han Lin, Tushar Nagarajan, Nicolas Ballas, Mido Assran, Mojtaba Komeili, Mohit Bansal, Koustuv Sinha,
• Abstract summary: We show that a strong off-the-shelf frozen pretrained visual encoder can achieve state-of-the-art (SoTA) performance in forecasting and procedural planning. By conditioning on frozen clip-level embeddings from observed steps to predict the actions of unseen steps, our prediction model is able to learn robust representations for forecasting.
• Score: 59.68917139718813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Procedural video representation learning is an active research area where the objective is to learn an agent which can anticipate and forecast the future given the present video input, typically in conjunction with textual annotations. Prior works often rely on large-scale pretraining of visual encoders and prediction models with language supervision. However, the necessity and effectiveness of extending compute intensive pretraining to learn video clip sequences with noisy text supervision have not yet been fully validated by previous works. In this work, we show that a strong off-the-shelf frozen pretrained visual encoder, along with a well designed prediction model, can achieve state-of-the-art (SoTA) performance in forecasting and procedural planning without the need for pretraining the prediction model, nor requiring additional supervision from language or ASR. Instead of learning representations from pixel space, our method utilizes the latent embedding space of publicly available vision encoders. By conditioning on frozen clip-level embeddings from observed steps to predict the actions of unseen steps, our prediction model is able to learn robust representations for forecasting through iterative denoising - leveraging the recent advances in diffusion transformers (Peebles & Xie, 2023). Empirical studies over a total of five procedural learning tasks across four datasets (NIV, CrossTask, COIN and Ego4D-v2) show that our model advances the strong baselines in long-horizon action anticipation (+2.6% in Verb ED@20, +3.1% in Noun ED@20), and significantly improves the SoTA in step forecasting (+5.0%), task classification (+3.8%), and procedure planning tasks (up to +2.28% in success rate, +3.39% in mAcc, and +0.90% in mIoU).

Related papers

• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• Early Action Recognition with Action Prototypes [62.826125870298306]
  We propose a novel model that learns a prototypical representation of the full action for each class. We decompose the video into short clips, where a visual encoder extracts features from each clip independently. Later, a decoder aggregates together in an online fashion features from all the clips for the final class prediction.
  arXiv  Detail & Related papers  (2023-12-11T18:31:13Z)
• Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction [15.696593695918844]
  This paper introduces a novel self-supervised video strategy for enhancing action prediction inspired by DINO (self-distillation with no labels) The experimental results showcase significant improvements in prediction performance across 3D-ResNet, Transformer, and LSTM architectures. These findings highlight the potential of our approach in diverse video-based tasks such as activity recognition, motion planning, and scene understanding.
  arXiv  Detail & Related papers  (2023-08-08T21:18:23Z)
• Multiscale Video Pretraining for Long-Term Activity Forecasting [67.06864386274736]
  Multiscale Video Pretraining learns robust representations for forecasting by learning to predict contextualized representations of future video clips over multiple timescales. MVP is based on our observation that actions in videos have a multiscale nature, where atomic actions typically occur at a short timescale and more complex actions may span longer timescales. Our comprehensive experiments across the Ego4D and Epic-Kitchens-55/100 datasets demonstrate that MVP out-performs state-of-the-art methods by significant margins.
  arXiv  Detail & Related papers  (2023-07-24T14:55:15Z)
• Rethinking Learning Approaches for Long-Term Action Anticipation [32.67768331823358]
  Action anticipation involves predicting future actions having observed the initial portion of a video. We introduce ANTICIPATR which performs long-term action anticipation. We propose a two-stage learning approach to train a novel transformer-based model.
  arXiv  Detail & Related papers  (2022-10-20T20:07:30Z)
• Distilling Knowledge from Language Models for Video-based Action Anticipation [31.59130630384036]
  Anticipating future actions in a video is useful for many autonomous and assistive technologies. We propose a method to make use of the text-modality that is available during the training, to bring in complementary information that is not present in the target action anticipation datasets.
  arXiv  Detail & Related papers  (2022-10-12T08:02:11Z)
• Reinforcement Learning with Action-Free Pre-Training from Videos [95.25074614579646]
  We introduce a framework that learns representations useful for understanding the dynamics via generative pre-training on videos. Our framework significantly improves both final performances and sample-efficiency of vision-based reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-25T19:44:09Z)
• Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation [57.68890534164427]
  In this work, we ask if we may leverage semi-supervised learning in unlabeled video sequences and extra images to improve the performance on urban scene segmentation. We simply predict pseudo-labels for the unlabeled data and train subsequent models with both human-annotated and pseudo-labeled data. Our Naive-Student model, trained with such simple yet effective iterative semi-supervised learning, attains state-of-the-art results at all three Cityscapes benchmarks.
  arXiv  Detail & Related papers  (2020-05-20T18:00:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.