Related papers: G-MIXER: Geodesic Mixup-based Implicit Semantic Ex…
Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works…
Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However,…
Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity…
Text-to-image (T2I) models have ushered in a new era of real-world image super-resolution (Real-ISR) due to their rich internal implicit knowledge for multimodal learning. Although bringing high-level semantic priors and dense pixel…
The explosive increase and ubiquitous accessibility of visual data on the Web have led to the prosperity of research activity in image search or retrieval. With the ignorance of visual content as a ranking clue, methods with text search…
Editing objects within a scene is a critical functionality required across a broad spectrum of applications in computer vision and graphics. As 3D Gaussian Splatting (3DGS) emerges as a frontier in scene representation, the effective…
Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification. Prior work assumes the modification text fully specifies the visual changes, overlooking after-effects and implicit consequences…
High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency.…
Retrieving fine-grained visual content based on user intent remains a challenge in multi-modal systems. Although current Composed Image Retrieval (CIR) methods combine reference images with retrieval texts, they are constrained to…
Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…
Cross-modal retrieval (CMR) is a fundamental task in multimedia research, focused on retrieving semantically relevant targets across different modalities. While traditional CMR methods match text and image via embedding-based similarity…
Most existing algorithms for cross-modal Information Retrieval are based on a supervised train-test setup, where a model learns to align the mode of the query (e.g., text) to the mode of the documents (e.g., images) from a given training…
Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine…
Mixup has become a popular augmentation strategy for image classification, yet its naive pixel-wise interpolation often produces unrealistic images that can hinder learning, particularly in high-stakes medical applications. We propose…
Many image restoration (IR) tasks require both pixel-level fidelity and high-level semantic understanding to recover realistic photos with fine-grained details. However, previous approaches often struggle to effectively leverage both the…
In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the…
With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large…
The recent growth of large foundation models that can easily generate pseudo-labels for huge quantity of unlabeled data makes unsupervised Zero-Shot Cross-Domain Image Retrieval (UZS-CDIR) less relevant. In this paper, we therefore turn our…
Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) often overlook…
Open-set semantic mapping enables language-driven robotic perception, but current instance-centric approaches are bottlenecked by context-depriving and computationally expensive crop-based feature extraction. To overcome this fundamental…