Related papers: Memory-Guided Semantic Learning Network for Tempor…
Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the…
Text information including extensive prior knowledge about land cover classes has been ignored in hyperspectral image classification (HSI) tasks. It is necessary to explore the effectiveness of linguistic mode in assisting HSI…
Most existing text-to-image generation methods adopt a multi-stage modular architecture which has three significant problems: 1) Training multiple networks increases the run time and affects the convergence and stability of the generative…
The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning…
Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic…
Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework…
We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents…
Sequential recommendation (SR) is to accurately recommend a list of items for a user based on her current accessed ones. While new-coming users continuously arrive in the real world, one crucial task is to have inductive SR that can produce…
Text classification plays an important role in various downstream text-related tasks, such as sentiment analysis, fake news detection, and public opinion analysis. Recently, text classification based on Graph Neural Networks (GNNs) has made…
The extraction of modular object-centric representations for downstream tasks is an emerging area of research. Learning grounded representations of objects that are guaranteed to be stable and invariant promises robust performance across…
Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning." Traditional gradient-based networks require a lot of data to learn, often through…
The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts…
Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…
Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species. In this paper, we introduce an effective and interpretable network module, the…
Memory-based Temporal Graph Neural Networks (MTGNNs) are a class of temporal graph neural networks that utilize a node memory module to capture and retain long-term temporal dependencies, leading to superior performance compared to…
Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimensional node-based feature representations that can be…
Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by the advancement of representation learning techniques and inspiration of human behaviors.…
We introduce a memory-based approach to part of speech tagging. Memory-based learning is a form of supervised learning based on similarity-based reasoning. The part of speech tag of a word in a particular context is extrapolated from the…
Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query…
Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head…