Papers with Code 아카이브

Image Retrieval with Multi-Modal Query

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 4
평가표: 3
보존된 평가 기록: 15

The problem of retrieving images from a database based on a multi-modal (image- text) query. Specifically, the query text prompts some modification in the query image and the task is to retrieve images with the desired modifications.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/cuthbertcai/ask-confirm

공식 코드

Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query

https://github.com/cwj1412/mscoco-flikcr30k_fg

공식 코드

Rethinking Benchmarks for Cross-modal Image-text Retrieval

https://github.com/danaesavi/socialmedia-textimage-classification-auxlosses

공식 코드

Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks

https://github.com/dandelin/vilt

공식 코드

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

https://github.com/deeplearnxmu/mm-mkp

공식 코드

Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering

https://github.com/delcayr/contextrefine-clip

공식 코드

ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025

https://github.com/descriptinc/lyrebird-wav2clip

공식 코드

Wav2CLIP: Learning Robust Audio Representations From CLIP

https://github.com/donnotnormal/dcgh

공식 코드

Deep Class-guided Hashing for Multi-label Cross-modal Retrieval

https://github.com/dopaminelcy/alta

공식 코드

Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models

https://github.com/e-bug/iglue

공식 코드

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

https://github.com/e-bug/volta

공식 코드

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

https://github.com/eanson023/rehamot

공식 코드

Cross-Modal Retrieval for Motion and Text via DopTriple Loss

https://github.com/echonet/echo_CLIP

공식 코드

Multimodal Foundation Models For Echocardiogram Interpretation

https://github.com/ecom-research/ComposeAE

공식 코드

Compositional Learning of Image-Text Query for Image Retrieval

https://github.com/epic-kitchens/epic-kitchens-100-annotations

공식 코드

Rescaling Egocentric Vision

https://github.com/epic-kitchens/epic-kitchens-100-narrator

공식 코드

Rescaling Egocentric Vision

https://github.com/eric-ai-lab/comclip

공식 코드

ComCLIP: Training-Free Compositional Image and Text Matching

https://github.com/eric-ai-lab/dsd

공식 코드

Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners

https://github.com/ethanjperez/film

공식 코드

FiLM: Visual Reasoning with a General Conditioning Layer

https://github.com/facebookresearch/imagebind

공식 코드

ImageBind: One Embedding Space To Bind Them All

https://github.com/fartashf/vsepp

공식 코드

VSE++: Improving Visual-Semantic Embeddings with Hard Negatives

https://github.com/flagai-open/flagai

공식 코드

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

https://github.com/flame-chasers/tbps-clip

공식 코드

An Empirical Study of CLIP for Text-based Person Search

https://github.com/fudannlplab/mousi

공식 코드

MouSi: Poly-Visual-Expert Vision-Language Models

https://github.com/ganchaofan0000/DAC

공식 코드

DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction

https://github.com/gingsi/coot-videotext

공식 코드

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

https://github.com/git-disl/seje

공식 코드

Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering

https://github.com/google-research-datasets/wit

공식 코드

AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation

https://github.com/google-research/google-research

공식 코드

Stacked Capsule Autoencoders

https://github.com/google-research/google-research/tree/master/fvlm/rovit

공식 코드

Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers

https://github.com/guoyang9/elip

공식 코드

ELIP: Efficient Language-Image Pre-training with Fewer Vision Tokens

https://github.com/gwatkinson/jump_download

공식 코드

Weakly supervised cross-modal learning in high-content screening

https://github.com/haixpham/CHEF

공식 코드

CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval

https://github.com/haowang1992/DSN

공식 코드

Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval

https://github.com/hcplab-sysu/personsearch-ctlg

공식 코드

Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search

https://github.com/hhc1997/l2rm

공식 코드

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.