Related papers: SPOLRE: Semantic Preserving Object Layout Reconstr…
After pre-training by generating the next word conditional on previous words, the Language Model (LM) acquires the ability of In-Context Learning (ICL) that can learn a new task conditional on the context of the given in-context examples…
Holographic cloud probes provide unprecedented information on cloud particle density, size and position. Each laser shot captures particles within a large volume, where images can be computationally refocused to determine particle size and…
Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation with human judgments…
Recent advances in reinforcement learning (RL) have predominantly leveraged neural network policies for decision-making, yet these models often lack interpretability, posing challenges for stakeholder comprehension and trust. Concept…
Unauthorized screen capturing and dissemination pose severe security threats such as data leakage and information theft. Several studies propose robust watermarking methods to track the copyright of Screen-Camera (SC) images, facilitating…
Image captioning is the generation of natural language descriptions of images which have increased immense popularity in the recent past. With this different deep-learning techniques are devised for the development of factual and stylized…
Recent advances in vision-language models have combined contrastive approaches with generative methods to achieve state-of-the-art (SOTA) on downstream inference tasks like zero-shot image classification. However, a persistent issue of…
The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high…
We study the problem of reconstructing an image from information stored at contour locations. We show that high-quality reconstructions with high fidelity to the source image can be obtained from sparse input, e.g., comprising less than…
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…
We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SRe$^2$L) that decouples the bilevel optimization of model and synthetic data during training, to handle varying scales of datasets, model architectures…
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from…
Image Captioning (IC) models can highly benefit from human feedback in the training process, especially in cases where data is limited. We present work-in-progress on adapting an IC system to integrate human feedback, with the goal to make…
We propose a semantic-aware neural reconstruction method to generate 3D high-fidelity models from sparse images. To tackle the challenge of severe radiance ambiguity caused by mismatched features in sparse input, we enrich neural implicit…
Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.…
Composed Image Retrieval (CIR) is the task of retrieving images matching a reference image augmented with a text, where the text describes changes to the reference image in natural language. Traditionally, models designed for CIR have…
Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. This underscores the critical need for dataset pruning, as the quality of these datasets is strongly correlated with the performance of VLMs on…
Iterative Language-Based Image Editing (IL-BIE) tasks follow iterative instructions to edit images step by step. Data scarcity is a significant issue for ILBIE as it is challenging to collect large-scale examples of images before and after…
Semantic image synthesis is a challenging task with many practical applications. Albeit remarkable progress has been made in semantic image synthesis with spatially-adaptive normalization and existing methods normalize the feature…
Recently, image captioning has aroused great interest in both academic and industrial worlds. Most existing systems are built upon large-scale datasets consisting of image-sentence pairs, which, however, are time-consuming to construct. In…