Related papers: Selective Structured State-Spaces for Long-Form Vi…
State-space models (SSMs) offer a powerful framework for dynamical system analysis, wherein the temporal dynamics of the system are assumed to be captured through the evolution of the latent states, which govern the values of the…
Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…
Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…
Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving…
State space models (SSMs) have emerged as a powerful framework for modelling long-range dependencies in sequence data. Unlike traditional recurrent neural networks (RNNs) and convolutional neural networks (CNNs), SSMs offer a structured and…
The role of long- and short-term dynamics towards salient object detection in videos is under-researched. We present a Transformer-based approach to learn a joint representation of video frames and past saliency information. Our model…
This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial…
We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a…
Recent studies in long video understanding have harnessed the advanced visual-language reasoning capabilities of Large Multimodal Models (LMMs), driving the evolution of video-LMMs specialized for processing extended video sequences.…
Recently, sequence learning methods have been applied to the problem of off-policy Reinforcement Learning, including the seminal work on Decision Transformers, which employs transformers for this task. Since transformers are…
In this work, we introduce S4M, a new efficient speech separation framework based on neural state-space models (SSM). Motivated by linear time-invariant systems for sequence modeling, our SSM-based approach can efficiently model input…
Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…
Segmentation of video objects in complex scenarios is highly challenging, and the MOSE dataset has significantly contributed to the development of this field. This technical report details the STSeg solution proposed by the "imaplus"…
Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…
The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features…
Sequential recommendation is a key area in the field of recommendation systems aiming to model user interest based on historical interaction sequences with irregular intervals. While previous recurrent neural network-based and…
We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term…
Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and…
Video Large Language Models (VLMs) have achieved strong performance on various vision-language tasks, yet their practical use is limited by the massive number of visual tokens produced from raw video frames, which quickly exhausts the…
In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…