Related papers: IDEA: Increasing Text Diversity via Online Multi-L…
Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…
Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with…
Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by…
Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less…
Tagging has been recognized as a successful practice to boost relevance matching for information retrieval (IR), especially when items lack rich textual descriptions. A lot of research has been done for either multi-label text…
In real-world applications, as data availability increases, obtaining labeled data for machine learning (ML) projects remains challenging due to the high costs and intensive efforts required for data annotation. Many ML projects,…
Continual learning aims to update a model so that it can sequentially learn new tasks without forgetting previously acquired knowledge. Recent continual learning approaches often leverage the vision-language model CLIP for its…
Although large-scale video-language pre-training models, which usually build a global alignment between the video and the text, have achieved remarkable progress on various downstream tasks, the idea of adopting fine-grained information…
Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…
This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering)…
Detecting text in natural scenes remains challenging, particularly for diverse scripts and arbitrarily shaped instances where visual cues alone are often insufficient. Existing methods do not fully leverage semantic context. This paper…
Assessing the aesthetics of an image is challenging, as it is influenced by multiple factors including composition, color, style, and high-level semantics. Existing image aesthetic assessment (IAA) methods primarily rely on human-labeled…
Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions. This enrichment…
Compared with single-label image classification, multi-label image classification is more practical and challenging. Some recent studies attempted to leverage the semantic information of categories for improving multi-label image…
Modeling label correlations has always played a pivotal role in multi-label image classification (MLC), attracting significant attention from researchers. However, recent studies have overemphasized co-occurrence relationships among labels,…
Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to…
Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…
Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly. In a visual understanding application, machines are expected to understand images like human.…
Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaining decent…
Legal multi-label classification is a critical task for organizing and accessing the vast amount of legal documentation. Despite its importance, it faces challenges such as the complexity of legal language, intricate label dependencies, and…