Related papers: Sub-sampled Cross-component Prediction for Emergin…
This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Coding for Machines (FCM). This standard aims at providing inter-operable compressed…
With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…
This paper presents a cross channel context model for latents in deep image compression. Generally, deep image compression is based on an autoencoder framework, which transforms the original image to latents at the encoder and recovers the…
There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling. We consider this observation to be important because having the solution sampling available makes the…
Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new scenarios remains expensive due to large-scale retraining and costly mean opinion score…
Element segmentation is a key step in nondestructive testing of Printed Circuit Boards (PCB) based on Computed Tomography (CT) technology. In recent years, the rapid development of self-supervised pretraining technology can obtain general…
Nowadays, real-time video communication over the internet through video conferencing applications has become an invaluable tool in everyone's professional and personal life. This trend underlines the need for video coding algorithms that…
Modern vision pipelines increasingly rely on pretrained image encoders whose representations are reused across tasks and models, yet these representations are often overcomplete and model-specific. We propose a simple, training-free method…
Most existing approaches for image and video compression perform transform coding in the pixel space to reduce redundancy. However, due to the misalignment between the pixel-space distortion and human perception, such schemes often face the…
Artifact removal and filtering methods are inevitable parts of video coding. On one hand, new codecs and compression standards come with advanced in-loop filters and on the other hand, displays are equipped with high capacity processing…
In recent years, the field of learned video compression has witnessed rapid advancement, exemplified by the latest neural video codecs DCVC-DC that has outperformed the upcoming next-generation codec ECM in terms of compression ratio.…
Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and uses low resolution feature maps. In the decoding process,…
Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and suboptimal performance. We propose Consistent Cross-layer…
Learned Compression (LC) is the emerging technology for compressing image and video content, using deep neural networks. Despite being new, LC methods have already gained a compression efficiency comparable to state-of-the-art image…
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder. Significant…
Large Vision-Language Models (LVLMs) are pivotal for real-world AI tasks like embodied intelligence due to their strong vision-language reasoning abilities. However, current LVLMs process entire images at the token level, which is…
Vision-based quality assessment in additive manufacturing often requires dedicated machine learning models and application-specific datasets. However, data collection and model training can be expensive and time-consuming. In this paper, we…
A transcoding scheme for the High Efficiency Video Coding (HEVC) is proposed that allows any partial frame modification to be followed by a partial re-compression of only the modified areas, while guaranteeing identical reconstruction of…
Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial perturbations. Existing methods primarily focus on adversarial fine-tuning or prompt…
In recent years, resolution adaptation based on deep neural networks has enabled significant performance gains for conventional (2D) video codecs. This paper investigates the effectiveness of spatial resolution resampling in the context of…