paper-with-me

Papers

ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval

2022-10-09 · Adriano Fragomeni, Michael Wray, Dima Damen

In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.

📄 PDF Abstract BibTeX arXiv:2210.04341

Code (1)

adrianofragomeni/contra 공식 구현 pytorch

Tasks

RetrievalSentenceSentence RetrievalVideo Retrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval

2021-03-28 · ICCV 2021 10 · Song Liu, Haoqi Fan, Shengsheng Qian, Yiru Chen 외

Video-Text Retrieval has been a hot research topic with the growth of multimedia data on the internet. Transformer for video-text learning has attracted increasing attention due to its promising performance. However, exi…

RetrievalText RetrievalVideo-Text Retrieval

Contrastive Video Question Answering via Video Graph Transformer

2023-02-27 · Junbin Xiao, Pan Zhou, Angela Yao, Yicong Li 외

We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer …

Contrastive LearningQuestion AnsweringVideo Question Answering

Contextual Augmented Global Contrast for Multimodal Intent Recognition

2024-01-01 · CVPR 2024 1 · Kaili Sun, Zhiwen Xie, Mang Ye, Huyin Zhang

Multimodal intent recognition (MIR) aims to perceive the human intent polarity via language visual and acoustic modalities. The inherent intent ambiguity makes it challenging to recognize in multimodal scenarios. Exi…

Contrastive LearningIntent RecognitionMultimodal Intent RecognitionMultimodal Sentiment Analysis+2

TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment

2021-08-23 · ICCV 2021 10 · Jianwei Yang, Yonatan Bisk, Jianfeng Gao

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade…

Action SegmentationContrastive LearningRepresentation LearningRetrieval+3

Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification

2024-01-08 · Wentao Zhu

In recent years, researchers combine both audio and video signals to deal with challenges where actions are not well represented or captured by visual cues. However, how to effectively leverage the two modalities is stil…

GPURepresentation LearningVideo Classification