Related papers: A request for clarity over the End of Sequence tok…
Extremely low-light text images are common in natural scenes, making scene text detection and recognition challenging. One solution is to enhance these images using low-light image enhancement methods before text extraction. However,…
Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or CLIP-Score fall short in this regard as they do not take into…
Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent…
End-to-end (E2E) spoken language understanding (SLU) is constrained by the cost of collecting speech-semantics pairs, especially when label domains change. Hence, we explore \textit{zero-shot} E2E SLU, which learns E2E SLU without…
Trusted execution environments (TEEs) provide an environment for running workloads in the cloud without having to trust cloud service providers, by offering additional hardware-assisted security guarantees. However, main memory encryption…
Conventional optical character recognition (OCR) techniques segmented each character and then recognized. This made them prone to error in character segmentation, and devoid of context to exploit language models. Advances in sequence to…
Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations, achieving efficient global modeling and reliable cross-modal…
Image paragraph captioning aims to describe a given image with a sequence of coherent sentences. Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences.…
Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text annotations. However, although these approaches perform well…
Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance…
Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties. To address this, we propose Concise-SAE, a training-free framework that improves…
Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…
Existing image captioning models are usually trained by cross-entropy (XE) loss and reinforcement learning (RL), which set ground-truth words as hard targets and force the captioning model to learn from them. However, the widely adopted…
The incremental sequence labeling task involves continuously learning new classes over time while retaining knowledge of the previous ones. Our investigation identifies two significant semantic shifts: E2O (where the model mislabels an old…
Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the…
To solve the Grammatical Error Correction (GEC) problem , a mapping between a source sequence and a target one is needed, where the two differ only on few spans. For this reason, the attention has been shifted to the non-autoregressive or…
Efficient distillation is a key pathway for converting expensive reasoning capability into deployable efficiency, yet in the frontier regime where the student already has strong reasoning ability, naive continual distillation often yields…
Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images. It is still challenging because ambiguity often occurs when the spacing between characters is large or the characters…
In this paper, we have worked on interpretability, trust, and understanding of the decisions made by models in the form of classification tasks. The task is divided into 3 subtasks. The first task consists of determining Binary Sexism…
Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous…