Related papers: Beyond Cosine Similarity: Zero-Initialized Residua…
Consider a spectrally sparse signal $\boldsymbol{x}$ that consists of $r$ complex sinusoids with or without damping. We study the robust recovery problem for the spectrally sparse signal under the fully observed setting, which is about…
End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…
Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships from seen classes to unseen classes. The core challenge is…
Arbitrary-shaped text detection has recently attracted increasing interests and witnessed rapid development with the popularity of deep learning algorithms. Nevertheless, existing approaches often obtain inaccurate detection results, mainly…
Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…
Aspect-category-based sentiment analysis (ACSA), which aims to identify aspect categories and predict their sentiments has been intensively studied due to its wide range of NLP applications. Most approaches mainly utilize intrasentential…
Scene-aware Adaptive Compressive Sensing (ACS) has attracted significant interest due to its promising capability for efficient and high-fidelity acquisition of scene images. ACS typically prescribes adaptive sampling allocation (ASA) based…
Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling, and obtain…
Medical image segmentation is usually regarded as one of the most important intermediate steps in clinical situations and medical imaging research. Thus, accurately assessing the segmentation quality of the automatically generated…
This work tackles the fidelity objective in the perceptual super-resolution~(SR). Specifically, we address the shortcomings of pixel-level $L_\text{p}$ loss ($\mathcal{L}_\text{pix}$) in the GAN-based SR framework. Since $L_\text{pix}$ is…
Recently, zero-shot anomaly detection (ZSAD) has emerged as a pivotal paradigm for industrial inspection and medical diagnostics, detecting defects in novel objects without requiring any target-dataset samples during training. Existing…
Aspect-based sentiment analysis (ABSA) is a crucial task in information extraction and sentiment analysis, aiming to identify aspects with associated sentiment elements in text. However, existing ABSA datasets are predominantly…
Training models for Aspect-Based Sentiment Analysis (ABSA) tasks requires manually annotated data, which is expensive and time-consuming to obtain. This paper introduces LA-ABSA, a novel approach that leverages Large Language Model…
We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction. The system is interpretable and user friendly and does not require labeled training data, hence can be rapidly and cost-effectively used across…
Aspect-based sentiment analysis (ABSA) generally requires a deep understanding of the contextual information, including the words associated with the aspect terms and their syntactic dependencies. Most existing studies employ advanced…
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity inference. It is challenging because a sentence may contain…
Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representations. However, these approaches heavily rely on manual…
Unified representation learning for multi-source data integration faces two important challenges: blockwise missingness and blockwise signal heterogeneity. The former arises from sources observing different, yet potentially overlapping,…
Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, which is essential for fine-grained opinion understanding in social media. Existing approaches…
Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on…