相关论文: Caption-Driven Explorations: Aligning Image and Te…

We present ZSE-Cap (Zero-Shot Ensemble for Captioning), our 4th place system in Event-Enriched Image Analysis (EVENTA) shared task on article-grounded image retrieval and captioning. Our zero-shot approach requires no finetuning on the…

Visual question answering (VQA) is known as an AI-complete task as it requires understanding, reasoning, and inferring about the vision and the language content. Over the past few years, numerous neural architectures have been suggested for…

Automatically describing video content with natural language has been attracting much attention in CV and NLP communities. Most existing methods predict one word at a time, and by feeding the last generated word back as input at the next…

Inspired by how the human brain employs a higher number of neural pathways when describing a highly focused subject, we show that deep attentive models used for the main vision-language task of image captioning, could be extended to achieve…

Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive…

This work introduces panoptic captioning, a novel task striving to seek the minimum text equivalent of images, which has broad potential applications. We take the first step towards panoptic captioning by formulating it as a task of…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…

In the field of image captioning, the phenomenon where missing or nonexistent objects are used to explain an image is referred to as object bias (or hallucination). To mitigate this issue, we propose a target-aware prompting strategy. This…

AI in dermatology is evolving at a rapid pace but the major limitation to training trustworthy classifiers is the scarcity of data with ground-truth concept level labels, which are meta-labels semantically meaningful to humans. Foundation…

The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image…

Concept-based interpretability methods are a popular form of explanation for deep learning models which provide explanations in the form of high-level human interpretable concepts. These methods typically find concept activation vectors…

State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…

Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through…

Autonomous mobile robots deployed in urban environments must be context-aware, i.e., able to distinguish between different semantic entities, and robust to occlusions. Current approaches like semantic scene completion (SSC) require…

Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of…

Optimizing vision models purely for classification accuracy can impose an alignment tax, degrading human-like scanpaths and limiting interpretability. We introduce EVA, a neuroscience-inspired hard-attention mechanistic testbed that makes…

Vision-to-language tasks aim to integrate computer vision and natural language processing together, which has attracted the attention of many researchers. For typical approaches, they encode image into feature representations and decode it…

Recent lightweight image captioning models using retrieved data mainly focus on text prompts. However, previous works only utilize the retrieved text as text prompts, and the visual information relies only on the CLIP visual embedding.…

Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the…

Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…