Related papers: Multifaceted Context Representation using Dual Att…

Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on…

Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification…

Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial intelligence. Two-stage approaches explicitly decouple DNN based perception from…

We introduce VocAlign, a novel source-free domain adaptation framework specifically designed for VLMs in open-vocabulary semantic segmentation. Our method adopts a student-teacher paradigm enhanced with a vocabulary alignment strategy,…

In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more,…

While there have been increased researches using deep learning techniques for the extraction of vascular structure from the 2D en face OCTA, for such approach, it is known that the data annotation process on the curvilinear structure like…

Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely…

Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment.…

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the…

Most previous studies integrate cognitive language processing signals (e.g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring…

Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many existing neural architectures, including Transformers,…

The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply of vision-and-language problems (such as Visual Question…

Deep neural networks can form high-level hierarchical representations of input data. Various researchers have demonstrated that these representations can be used to enable a variety of useful applications. However, such representations are…

The monocular depth estimation task has recently revealed encouraging prospects, especially for the autonomous driving task. To tackle the ill-posed problem of 3D geometric reasoning from 2D monocular images, multi-frame monocular methods…

Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which…

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency…

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to…

Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try to overcome this problem by processing video or stereo sequences, which may not always be…

Visual entailment (VE) is to recognize whether the semantics of a hypothesis text can be inferred from the given premise image, which is one special task among recent emerged vision and language understanding tasks. Currently, most of the…

Despite the large number of patients in Electronic Health Records (EHRs), the subset of usable data for modeling outcomes of specific phenotypes are often imbalanced and of modest size. This can be attributed to the uneven coverage of…