Related papers: TIE: Time Interval Encoding for Video Generation o…
Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fields, which might incur numerous irrelevant cues, such as a…
The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…
The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…
Multivariate time series forecasting (MTSF) plays a vital role in a wide range of real-world applications, such as weather prediction and traffic flow forecasting. Although recent advances have significantly improved the modeling of…
Graph neural Ordinary Differential Equations (ODE) combine neural ODE with the message passing mechanism of Graph Neural Networks (GNN), providing a continuous-time modeling method for graph representation learning. However, in dynamic…
This paper addresses the challenge of capturing global temporaldependencies in long video sequences for Video Object Segmentation (VOS). Existing architectures often fail to effectively model these dependencies acrossextended temporal…
Multimodal time series forecasting is foundational in various fields, such as utilizing satellite imagery and numerical data for predicting typhoons in climate science. However, existing multimodal approaches primarily focus on utilizing…
Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over…
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…
End-to-end visual information extraction (VIE) aims at integrating the hierarchical subtasks of VIE, including text spotting, word grouping, and entity labeling, into a unified framework. Dealing with the gaps among the three subtasks plays…
With the increasing demands on e-commerce platforms, numerous user action history is emerging. Those enriched action records are vital to understand users' interests and intents. Recently, prior works for user behavior prediction mainly…
Simulating time evolution under quantum Hamiltonians is one of the most natural applications of quantum computers. We introduce TE-PAI, which simulates time evolution exactly by sampling random quantum circuits for the purpose of estimating…
Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-dimensional…
Continuous-time models are a natural choice for irregular and asynchronous data. A central design choice is how to embed discrete observations into continuous time. Interpolation- and imputation-based embeddings reconstruct a continuous…
Recent Continuous Thought Machine architecture decouples internal computation from external inputs via neural dynamics, but relies on multi-layer perceptrons without stability guarantees. We propose to model neural dynamics using asymmetric…
A prominent paradigm for graph neural networks is based on the message-passing framework. In this framework, information communication is realized only between neighboring nodes. The challenge of approaches that use this paradigm is to…
Identifying key temporal intervals within long videos, known as temporal grounding (TG), is important to video understanding and reasoning tasks. In this paper, we introduce a new form of the temporal grounding problem,…
Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically…
Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed…
Mapping sequences of discrete data to a point in a continuous space makes it difficult to retrieve those sequences via random sampling. Mapping the input to a volume would make it easier to retrieve at test time, and that's the strategy…