相关论文: Context Guided Transformer Entropy Modeling for Vi…

The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant…

In-context learning is a remarkable capability of transformers, referring to their ability to adapt to specific tasks based on a short history or context. Previous research has found that task-specific information is locally encoded within…

Current video representations heavily rely on learning from manually annotated video datasets which are time-consuming and expensive to acquire. We observe videos are naturally accompanied by abundant text information such as YouTube titles…

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…

There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained…

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a…

Transformer-based models have demonstrated considerable potential for source code modeling tasks in software engineering. However, they are limited by their dependence solely on automatic self-attention weight learning mechanisms. Previous…

Conventional image denoising models often inadvertently learn spurious correlations between environmental factors and noise patterns. Moreover, due to high-frequency ambiguity, they struggle to reliably distinguish subtle textures from…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

We consider an online decision making setting known as contextual bandit problem, and propose an approach for improving contextual bandit performance by using an adaptive feature extraction (representation learning) based on online…

Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial…

Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input…

There have been several attempts at modeling context in robots. However, either these attempts assume a fixed number of contexts or use a rule-based approach to determine when to increment the number of contexts. In this paper, we pose the…

We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…

Contemporary lossy image and video coding standards rely on transform coding, the process through which pixels are mapped to an alternative representation to facilitate efficient data compression. Despite impressive performance of…

Data driven methods for time series forecasting that quantify uncertainty open new important possibilities for robot tasks with hard real time constraints, allowing the robot system to make decisions that trade off between reaction time and…

Feature selection is a crucial tool in machine learning and is widely applied across various scientific disciplines. Traditional supervised methods generally identify a universal set of informative features for the entire population.…

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned…

In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static.…

Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…