paper-with-me

홈 › Papers

Weakly-Supervised Alignment of Video With Text

2015-05-22 · ICCV 2015 12 · Piotr Bojanowski, Rémi Lajugie, Edouard Grave, Francis Bach, Ivan Laptev, Jean Ponce, Cordelia Schmid

Suppose that we are given a set of videos, along with natural language descriptions in the form of multiple sentences (e.g., manual annotations, movie scripts, sport summaries etc.), and that these sentences appear in the same temporal order as their visual counterparts. We propose in this paper a method for aligning the two modalities, i.e., automatically providing a time stamp for every sentence. Given vectorial features for both video and text, we propose to cast this task as a temporal assignment problem, with an implicit linear mapping between the two feature modalities. We formulate this problem as an integer quadratic program, and solve its continuous convex relaxation using an efficient conditional gradient algorithm. Several rounding procedures are proposed to construct the final integer solution. After demonstrating significant improvements over the state of the art on the related task of aligning video with symbolic labels [7], we evaluate our method on a challenging dataset of videos with associated textual descriptions [36], using both bag-of-words and continuous representations for text.

📄 PDF Abstract BibTeX arXiv:1505.06027

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Similar Papers 제목 키워드 기반

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

2022-03-31 · CVPR 2022 1 · Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh 외

Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated a…

Contrastive LearningDynamic Time WarpingRepresentation Learning

wMAN: WEAKLY-SUPERVISED MOMENT ALIGNMENT NETWORK FOR TEXT-BASED VIDEO SEGMENT RETRIEVAL

2019-09-25 · Reuben Tan, Huijuan Xu, Kate Saenko, Bryan A. Plummer

Given a video and a sentence, the goal of weakly-supervised video moment retrieval is to locate the video segment which is described by the sentence without having access to temporal annotations during training. Instead…

Moment RetrievalRetrievalSentence

WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding

2023-01-01 · CVPR 2023 1 · Mengze Li, Han Wang, Wenqiao Zhang, Jiaxu Miao 외

Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a language query. Existing techniques achieve such alignment by exploiting dense boundary and bounding box annotations, which can …

Contrastive LearningSpatio-Temporal Video GroundingVideo Grounding

Learning from Video and Text via Large-Scale Discriminative Clustering

2017-07-27 · ICCV 2017 10 · Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev 외

Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks. Such applications include person and action recognition, text-to-video alignment, object co-segmentation and coloca…

Action RecognitionClusteringTemporal Action LocalizationVideo Alignment+3

Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding

2022-10-21 · Findings (EMNLP) 2021 11 · Yuechen Wang, Wengang Zhou, Houqiang Li

Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels, we are…

cross-modal alignmentSentence