RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos

• URL: http://arxiv.org/abs/2403.18600v2
• Date: Wed, 25 Sep 2024 14:20:39 GMT
• Title: RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos
• Authors: Ali Zare, Yulei Niu, Hammad Ayyubi, Shih-fu Chang,
• Abstract summary: We propose a new and practical setting, called adaptive procedure planning in instructional videos. RAP adaptively determines the conclusion of actions using an auto-regressive model architecture.
• Score: 46.26690150997731
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Procedure Planning in instructional videos entails generating a sequence of action steps based on visual observations of the initial and target states. Despite the rapid progress in this task, there remain several critical challenges to be solved: (1) Adaptive procedures: Prior works hold an unrealistic assumption that the number of action steps is known and fixed, leading to non-generalizable models in real-world scenarios where the sequence length varies. (2) Temporal relation: Understanding the step temporal relation knowledge is essential in producing reasonable and executable plans. (3) Annotation cost: Annotating instructional videos with step-level labels (i.e., timestamp) or sequence-level labels (i.e., action category) is demanding and labor-intensive, limiting its generalizability to large-scale datasets. In this work, we propose a new and practical setting, called adaptive procedure planning in instructional videos, where the procedure length is not fixed or pre-determined. To address these challenges, we introduce Retrieval-Augmented Planner (RAP) model. Specifically, for adaptive procedures, RAP adaptively determines the conclusion of actions using an auto-regressive model architecture. For temporal relation, RAP establishes an external memory module to explicitly retrieve the most relevant state-action pairs from the training videos and revises the generated procedures. To tackle high annotation cost, RAP utilizes a weakly-supervised learning manner to expand the training dataset to other task-relevant, unannotated videos by generating pseudo labels for action steps. Experiments on CrossTask and COIN benchmarks show the superiority of RAP over traditional fixed-length models, establishing it as a strong baseline solution for adaptive procedure planning.

Related papers

• Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos [48.15438373870542]
  VidAssist is an integrated framework designed for zero/few-shot goal-oriented planning in instructional videos. It employs a breadth-first search algorithm for optimal plan generation. Experiments demonstrate that VidAssist offers a unified framework for different goal-oriented planning setups.
  arXiv  Detail & Related papers  (2024-09-30T17:57:28Z)
• Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos [16.333295670635557]
  We explore the capability of an agent to construct a logical sequence of action steps, thereby assembling a strategic procedural plan. This plan is crucial for navigating from an initial visual observation to a target visual outcome, as depicted in real-life instructional videos. We coin our approach KEPP, a novel Knowledge-Enhanced Procedure Planning system, which harnesses a probabilistic procedural knowledge graph extracted from training data.
  arXiv  Detail & Related papers  (2024-03-05T08:55:51Z)
• POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization [26.506893363676678]
  This paper proposes POTLoc, a Pseudo-label Oriented Transformer for weakly-supervised Action localization. POTLoc is designed to identify and track continuous action structures via a self-training strategy. It outperforms the state-of-the-art point-supervised methods on THUMOS'14 and ActivityNet-v1.2 datasets.
  arXiv  Detail & Related papers  (2023-10-20T15:28:06Z)
• Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning [85.84504287685884]
  Skip-Plan is a condensed action space learning method for procedure planning in instructional videos. By skipping uncertain nodes and edges in action chains, we transfer long and complex sequence functions into short but reliable ones. Our model explores all sorts of reliable sub-relations within an action sequence in the condensed action space.
  arXiv  Detail & Related papers  (2023-10-01T08:02:33Z)
• Learning and Verification of Task Structure in Instructional Videos [85.511888642497]
  We introduce a new pre-trained video model, VideoTaskformer, focused on representing the semantics and structure of instructional videos. Compared to prior work which learns step representations locally, our approach involves learning them globally. We introduce two new benchmarks for detecting mistakes in instructional videos, to verify if there is an anomalous step and if steps are executed in the right order.
  arXiv  Detail & Related papers  (2023-03-23T17:59:54Z)
• P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision [31.73732506824829]
  We study the problem of procedure planning in instructional videos. Here, an agent must produce a plausible sequence of actions that can transform the environment from a given start to a desired goal state. We propose a weakly supervised approach by learning from natural language instructions.
  arXiv  Detail & Related papers  (2022-05-04T19:37:32Z)
• Learning To Recognize Procedural Activities with Distant Supervision [96.58436002052466]
  We consider the problem of classifying fine-grained, multi-step activities from long videos spanning up to several minutes. Our method uses a language model to match noisy, automatically-transcribed speech from the video to step descriptions in the knowledge base.
  arXiv  Detail & Related papers  (2022-01-26T15:06:28Z)
• SVIP: Sequence VerIfication for Procedures in Videos [68.07865790764237]
  We propose a novel sequence verification task that aims to distinguish positive video pairs performing the same action sequence from negative ones with step-level transformations. Such a challenging task resides in an open-set setting without prior action detection or segmentation. We collect a scripted video dataset enumerating all kinds of step-level transformations in chemical experiments.
  arXiv  Detail & Related papers  (2021-12-13T07:03:36Z)
• STRIPS Action Discovery [67.73368413278631]
  Recent approaches have shown the success of classical planning at synthesizing action models even when all intermediate states are missing. We propose a new algorithm to unsupervisedly synthesize STRIPS action models with a classical planner when action signatures are unknown.
  arXiv  Detail & Related papers  (2020-01-30T17:08:39Z)

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.