相关论文: Video Prediction Recalling Long-term Motion Contex…

In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame…

Forecasting the future traffic flow distribution in an area is an important issue for traffic management in an intelligent transportation system. The key challenge of traffic prediction is to capture spatial and temporal relations between…

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

We propose a hierarchical approach for making long-term predictions of future frames. To avoid inherent compounding errors in recursive pixel-level prediction, we propose to first estimate high-level structure in the input frames, then…

Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explicit spatial alignment can successfully recover fine details in controlled environments, it…

Urban environments manifest a high level of complexity, and therefore it is of vital importance for safety systems embedded within autonomous vehicles (AVs) to be able to accurately predict the short-term future motion of nearby agents.…

Vision-language-action (VLA) models for closed-loop robot control are typically cast under the Markov assumption, making them prone to errors on tasks requiring historical context. To incorporate memory, existing VLAs either retrieve from a…

Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, where models lose previously acquired knowledge…

Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…

Multimodal large language models (MLLMs) have demonstrated strong performance in understanding videos holistically, yet their ability to process streaming videos-videos are treated as a sequence of visual events-remains underexplored.…

Many methods have been developed to help people find the video contents they want efficiently. However, there are still some unsolved problems in this area. For example, given a query video and a reference video, how to accurately localize…

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…

Autonomous vehicles are expected to drive in complex scenarios with several independent non cooperating agents. Path planning for safely navigating in such environments can not just rely on perceiving present location and motion of other…

Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing…

Motion forecasting represents a critical challenge in autonomous driving systems, requiring accurate prediction of surrounding agents' future trajectories. While existing approaches predict future motion states with the extracted scene…

Autoregressive (AR) video diffusion has recently emerged as a promising paradigm for long video generation, enabling causal synthesis beyond the limits of bidirectional models. To address training-inference mismatch, a series of…

Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing…

In this paper, the problem of head movement prediction for virtual reality videos is studied. In the considered model, a deep learning network is introduced to leverage position data as well as video frame content to predict future head…

Motion prediction is a classic problem in computer vision, which aims at forecasting future motion given the observed pose sequence. Various deep learning models have been proposed, achieving state-of-the-art performance on motion…

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…