Related papers: TSM: Temporal Shift Module for Efficient and Scala…
In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its simplicity late fusion is still the predominant approach in many…
Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To…
Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison,…
An important aspect of video understanding is the ability to predict the evolution of its content in the future. This paper presents a future frame semantic segmentation technique for predicting semantic masks of the current and future…
Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal context, redundant…
We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features…
We present 2SDS (Scene Separation and Data Selection algorithm), a temporal segmentation algorithm used in real-time video stream interpretation. It complements CNN-based models to make use of temporal information in videos. 2SDS can detect…
Multimodal foundation models (MFMs) have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. However, these models face inherent limitations due to their finite internal…
Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term memory due to the high computational cost associated with…
Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively…
Existing Mamba-based approaches in remote sensing change detection have enhanced scanning models, yet remain limited by their inability to capture long-range dependencies between image channels effectively, which restricts their feature…
3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…
This paper describes a temporal-spatial model for video processing with special applications to processing event camera videos. We propose to study a conjecture motivated by our previous study of video processing with delay loop reservoir…
Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…
This paper presents the first-rank solution for the Multi-Modal Action Recognition Challenge, part of the Multi-Modal Visual Pattern Recognition Workshop at the \acl{ICPR} 2024. The competition aimed to recognize human actions using a…
Processing long videos with multimodal large language models (MLLMs) poses a significant computational challenge, as the model's self-attention mechanism scales quadratically with the number of video tokens, resulting in high computational…
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…
Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address this limitation, we curate a dedicated instruction fine-tuning…
Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…
Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively…