相关论文: Disentangled Counterfactual Learning for Physical …

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to…

Multi-view clustering can explore common semantics from multiple views and has received increasing attention in recent years. However, current methods focus on learning consistency in representation, neglecting the contribution of each…

Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing…

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video transformer which are used in parallel to generate diverse…

We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation…

A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typically k-means, to produce pseudo-labels that guide training,…

Deep neural networks (DNNs) often struggle with out-of-distribution data, limiting their reliability in diverse realworld applications. To address this issue, domain generalization methods have been developed to learn domain-invariant…

Video-grounded dialogue systems aim to integrate video understanding and dialogue understanding to generate responses that are relevant to both the dialogue and video context. Most existing approaches employ deep learning models and have…

Multimodal recommendation systems integrate diverse multimodal information into the feature representations of both items and users, thereby enabling a more comprehensive modeling of user preferences. However, existing methods are hindered…

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…

The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships.…

Audio-visual segmentation (AVS) aims to segment objects in videos based on audio cues. Existing AVS methods are primarily designed to enhance interaction efficiency but pay limited attention to modality representation discrepancies and…

Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of…

Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is important when applying deep neural networks (DNNs) in fields…

Image recognition is a classic and common task in the computer vision field, which has been widely applied in the past decade. Most existing methods in literature aim to learn discriminative features from labeled images for classification,…