Related papers: DDLP: Unsupervised Object-Centric Video Prediction…
Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…
Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…
The attention mechanism has become a go-to technique for natural language processing and computer vision tasks. Recently, the MLP-Mixer and other MLP-based architectures, based simply on multi-layer perceptrons (MLPs), are also powerful…
Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…
Our goal in this work is to generate realistic videos given just one initial frame as input. Existing unsupervised approaches to this task do not consider the fact that a video typically shows a 3D environment, and that this should remain…
As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…
A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat images holistically and rely on text conditioning, creating…
Prompt learning is an effective way to exploit the potential of large-scale pre-trained foundational models. Continuous prompts parameterize context tokens in prompts by turning them into differentiable vectors. Deep continuous prompts…
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning…
This study builds on the architecture of the Disentangler of Visual Priors (DVP), a type of autoencoder that learns to interpret scenes by decomposing the perceived objects into independent visual aspects of shape, size, orientation, and…
Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…
Video anomaly detection is recently formulated as a multiple instance learning task under weak supervision, in which each video is treated as a bag of snippets to be determined whether contains anomalies. Previous efforts mainly focus on…
World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformerbased models significantly hinders real-time deployment. To address this efficiency-performance…
The performance of Visio-Language Transformers drops sharply when an input modality (e.g., image) is missing, because the model is forced to make predictions using incomplete information. Existing missing-aware prompt methods help reduce…
Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually close to geometric primitives…
Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from…
Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. Existing methods often rely on the score matching from 3D boxes or pre-trained diffusion priors. However, they typically require…
Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video…
This paper presents WALDO (WArping Layer-Decomposed Objects), a novel approach to the prediction of future video frames from past ones. Individual images are decomposed into multiple layers combining object masks and a small set of control…