Related papers: Skin Tokens: A Learned Compact Representation for …

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition…

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making,…

Representation (feature) space is an environment where data points are vectorized, distances are computed, patterns are characterized, and geometric structures are embedded. Extracting a good representation space is critical to address the…

Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from inefficiency, either due to token-by-token…

We present an effective method for fusing visual-and-language representations for several question answering tasks including visual question answering and visual entailment. In contrast to prior works that concatenate unimodal…

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

We propose a novel deep reinforcement learning-based approach for 3D object reconstruction from monocular images. Prior works that use mesh representations are template based. Thus, they are limited to the reconstruction of objects that…

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

We introduce ResGen, an efficient Residual Vector Quantization (RVQ)-based generative model for high-fidelity generation with fast sampling. RVQ improves data fidelity by increasing the number of quantization steps, referred to as depth,…

1. Research question: With the growing interest in skin diseases and skin aesthetics, the ability to predict facial wrinkles is becoming increasingly important. This study aims to evaluate whether a computational model, convolutional neural…

3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art…

Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute especially at inference time. To address this problem, we propose Mask-LLaVA, a…

Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent…

Neural implicit representations have shown substantial improvements in efficiently storing 3D data, when compared to conventional formats. However, the focus of existing work has mainly been on storage and subsequent reconstruction. In this…

Secondary animation effects are essential for liveliness. We propose a simple, real-time solution for adding them on top of standard skinning, enabling artist-driven stylization of skeletal motion. Our method takes a standard skeleton…

Transformers have demonstrated strong potential in offline reinforcement learning (RL) by modeling trajectories as sequences of return-to-go, states, and actions. However, existing approaches such as the Decision Transformer(DT) and its…

In the last years, the computer vision research community has studied on how to model temporal dynamics in videos to employ 3D human action recognition. To that end, two main baseline approaches have been researched: (i) Recurrent Neural…

Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in…

Skeletonization is a popular shape analysis technique that models an object's interior as opposed to just its boundary. Fitting template-based skeletal models is a time-consuming process requiring much manual parameter tuning. Recently,…