Composed Image Retrieval
PulseAugur coverage of Composed Image Retrieval — every cluster mentioning Composed Image Retrieval across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AutoConcept improves metadata-aware image retrieval without training
Researchers have developed AutoConcept, a novel training-free reranking method for composed image retrieval (CIR) that leverages metadata to improve results. This approach converts concept evidence into an interpretable…
-
PeFuse framework uses Diffusion Models and LLMs for training-free Composed Image Retrieval
Researchers have developed PeFuse, a novel training-free framework for Composed Image Retrieval (CIR). This method utilizes pre-trained Diffusion Models and Multimodal Large Language Models to bridge visual and textual …
-
EviRank paper introduces structured evidence for multimodal image re-ranking
Researchers have introduced EviRank, a novel method for multimodal image re-ranking that treats queries as semantic constraint satisfaction problems. EviRank parses queries into structured evidence packages, detailing r…
-
New TDIR Algorithm Enhances Historical Image Retrieval
Researchers have developed Temporally Decomposable Image Representations (TDIR), a novel algorithm designed to improve image and object retrieval from historical photographs. TDIR works by decomposing images into separa…
-
FiRE enhances MLLMs for complex image retrieval with fine-grained context learning · 3 sources tracked
Researchers have developed FiRE, a novel approach to enhance Multimodal Large Language Models (MLLMs) for complex image retrieval tasks. FiRE introduces a fine-grained context learning strategy that involves a two-stage…
-
Vision-Free CIR Framework Enhances Image Retrieval with LLM Reranking
Researchers have developed a novel vision-free framework for Composed Image Retrieval (CIR), a complex multimodal task. This approach utilizes Attribute-Augmented Hybrid Scoring to compensate for visual details lost in …
-
New frameworks enhance zero-shot composed image retrieval accuracy
Two new research papers introduce novel frameworks for zero-shot composed image retrieval, a task that involves identifying a target image based on a reference image and a textual modification. The first paper, PEC-CIR,…
-
New research tackles zero-shot retrieval with advanced AI frameworks · 2 sources tracked
Two new research papers explore advanced retrieval techniques for large-scale zero-shot scenarios. One paper introduces EMMETT and IRENE, frameworks designed to synthesize classifiers on-the-fly for novel items, improvi…
-
New Composed Object Retrieval task enables object-level image search
Researchers have introduced Composed Object Retrieval (COR), a novel task designed to enable object-level retrieval within images using composed expressions. Unlike existing Composed Image Retrieval (CIR) methods that m…
-
New CLARA framework uses visual alternatives to resolve image retrieval ambiguity
Researchers have introduced CLARA, a novel framework designed to address ambiguity in composed image retrieval (CIR). Unlike previous methods that rely on text-based clarification, CLARA presents users with a small sele…
-
RankVR framework enhances image retrieval by filtering noisy data
Researchers have introduced RankVR, a new framework designed to improve Composed Image Retrieval (CIR) models. RankVR addresses challenges in large datasets, specifically noisy triplet correspondence, by employing a Glo…
-
New IMAGINE network enhances video retrieval with implicit semantics
Researchers have developed IMAGINE, a novel network designed for Composed Video Retrieval (CVR) and Composed Image Retrieval (CIR). This system addresses the limitation of existing methods by incorporating implicit sema…
-
COMBINER network improves image retrieval with attribute-based relations
Researchers have developed COMBINER, a novel network for composed image retrieval that addresses the challenge of visually similar but semantically different images. The system utilizes attribute prototypes to create a …
-
New framework tackles ambiguity in image retrieval with clarifying questions
Researchers have introduced a new framework for Composed Image Retrieval (CIR) that addresses the inherent ambiguity in queries. Unlike previous systems that assume a single target image, this approach reframes CIR as c…
-
New benchmark and dataset advance satellite image retrieval
Researchers have developed a new benchmark for Composed Image Retrieval (CIR) specifically tailored for Earth Observation (EO) data. This benchmark evaluates existing CIR methods on satellite imagery, revealing that tra…
-
CIR benchmarks overestimate AI model composition abilities
A new research paper questions the effectiveness of current benchmarks for Composed Image Retrieval (CIR), a task requiring models to combine image and text information. The study found that many existing CIR benchmarks…
-
TEMA architecture improves composed image retrieval with multi-modification capabilities
Researchers have introduced TEMA, a novel Text-oriented Entity Mapping Architecture designed to improve Composed Image Retrieval (CIR). This new framework addresses limitations in existing CIR systems, such as insuffici…
-
Air-Know network tackles composed image retrieval with novel expert-proxy-diversion paradigm
Researchers have introduced Air-Know, a novel network designed to tackle the Composed Image Retrieval (CIR) challenge, specifically addressing the Noisy Triplet Correspondence (NTC) problem. Existing methods struggle wi…