Related papers: SkillRater: Untangling Capabilities in Multimodal …
Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…
Representation learning is important for solving sequence-to-sequence problems in natural language processing. Representation learning transforms raw data into vector-form representations while preserving their features. However, data with…
Dimension of the encoder output (i.e., the code layer) in an autoencoder is a key hyper-parameter for representing the input data in a proper space. This dimension must be carefully selected in order to guarantee the desired reconstruction…
Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The…
In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks. Despite impressive advances, scalability and evaluation remain prevalent issues.…
Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a…
Solving different types of optimization models (including parameters fitting) for support vector machines on large-scale training data is often an expensive computational task. This paper proposes a multilevel algorithmic framework that…
Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some…
Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number…
In this paper, we train independent linear decoder models to estimate the perceived quality of images. More specifically, we calculate the responses of individual non-overlapping image patches to each of the decoders and scale these…
Learning visual feature representations for video analysis is a daunting task that requires a large amount of training samples and a proper generalization framework. Many of the current state of the art methods for video captioning and…
Classical video quality assessment methods generate a numerical score to judge a video's perceived visual fidelity and clarity. Yet, a score fails to describe the video's complex quality dimensions, restricting its applicability. Benefiting…
Photo Rater is a computer vision project that uses neural networks to help photographers select the best photo among those that are taken based on the same scene. This process is usually referred to as "culling" in photography, and it can…
Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binary classifier to…
Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic. However, the effectiveness of these VLMs critically depends on high-quality image-text training…
Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences. Existing In-Context-Learning based…
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…
Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval…
Modern high-dimensional methods often adopt the "bet on sparsity" principle, while in supervised multivariate learning statisticians may face "dense" problems with a large number of nonzero coefficients. This paper proposes a novel…