REVIEW 6 cited by
ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
An intuitive way to search for images is to use queries composed of an example image and a complementary text. While the first provides rich and implicit context for the search, the latter explicitly calls for new traits, or specifies how some elements of the example image should be changed to retrieve the desired target image. Current approaches typically combine the features of each of the two elements of the query into a single representation, which can then be compared to the ones of the potential target images. Our work aims at shedding new light on the task by looking at it through the prism of two familiar and related frameworks: text-to-image and image-to-image retrieval. Taking inspiration from them, we exploit the specific relation of each query element with the targeted image and derive light-weight attention mechanisms which enable to mediate between the two complementary modalities. We validate our approach on several retrieval benchmarks, querying with images and their associated free-form text modifiers. Our method obtains state-of-the-art results without resorting to side information, multi-level features, heavy pre-training nor large architectures as in previous works.
Forward citations
Cited by 6 Pith papers
-
Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval
FoCo learns composition for zero-shot CIR via text-anchored visual aggregation and context-conditioned semantic completion trained jointly with cross-instance contrastive loss, reporting SOTA on four benchmarks.
-
Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets
ZeroSight supplies a video-derived dataset and evaluation protocol for genuine zero-shot composed image retrieval plus the SC4CIR consistency method, demonstrating that prior benchmarks inflate reported performance ac...
-
Mixed-Modality Dual Face-Hair Retrieval
Introduces DFHR task, DFHR-Bench with over 180K triplets, and MFHC framework for mixed-modality dual face-hair retrieval.
-
STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval
STiTch refines LLM captions via embedding transition and uses set-to-set bidirectional transportation alignment to improve training-free zero-shot composed image retrieval.
-
Beyond Simple Edits: Composed Video Retrieval with Dense Modifications
A new benchmark with much longer, denser modification texts, plus a single-encoder fusion model, raises composed video retrieval Recall@1 by 3.4 points on its own test set.
-
FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval
FAR-Net combines Q-Former cross-attention alignment with uncertainty-perturbed contrastive learning and reports up to 2.4 points higher Recall@1 on standard CIR benchmarks.
Discussion (0). Sign in to comment.