Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation

Multi-modal recommendation greatly enhances the performance of recommender systems by modeling the auxiliary information from multi-modality contents. Most existing multi-modal recommendation models primarily exploit multimedia information propagation processes to enrich item representations and directly utilize modal-specific embedding vectors independently obtained from upstream pre-trained models. However, this might be inappropriate since the abundant task-specific semantics remain unexplored, and the cross-modality semantic gap hinders the recommendation performance. Inspired by the recent progress of the cross-modal alignment model CLIP, in this paper, we propose a novel \textbf{CLIP} \textbf{E}nhanced \textbf{R}ecommender (\textbf{CLIPER}) framework to bridge the semantic gap between modalities and extract fine-grained multi-view semantic information. Specifically, we introduce a multi-view modality-alignment approach for representation extraction and measure the semantic similarity between modalities. Furthermore, we integrate the multi-view multimedia representations into downstream recommendation models. Extensive experiments conducted on three public datasets demonstrate the consistent superiority of our model over state-of-the-art multi-modal recommendation models.

VCoME: Verbal Video Composition with Multimodal Editing Effects

Verbal videos, featuring voice-overs or text overlays, provide valuable content but present significant challenges in composition, especially when incorporating editing effects to enhance clarity and visual appeal. In this paper, we introduce the novel task of verbal video composition with editing effects. This task aims to generate coherent and visually appealing verbal videos by integrating multimodal editing effects across textual, visual, and audio categories. To achieve this, we curate a large-scale dataset of video effects compositions from publicly available sources. We then formulate this task as a generative problem, involving the identification of appropriate positions in the verbal content and the recommendation of editing effects for these positions. To address this task, we propose VCoME, a general framework that employs a large multimodal model to generate editing effects for video composition. Specifically, VCoME takes in the multimodal video context and autoregressively outputs where to apply effects within the verbal content and which effects are most appropriate for each position. VCoME also supports prompt-based control of composition density and style, providing substantial flexibility for diverse applications. Through extensive quantitative and qualitative evaluations, we clearly demonstrate the effectiveness of VCoME. A comprehensive user study shows that our method produces videos of professional quality while being 85$\times$ more efficient than professional editors.

Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey

Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation. The skip connection has played an essential role in the architecture of deep neural networks,enabling easier optimization through residual learning during the training stage and improving accuracy during testing. Many neural networks have inherited the idea of residual learning with skip connections for various tasks, and it has been the standard choice for designing neural networks. This survey provides a comprehensive summary and outlook on the development of skip connections in deep neural networks. The short history of skip connections is outlined, and the development of residual learning in deep neural networks is surveyed. The effectiveness of skip connections in the training and testing stages is summarized, and future directions for using skip connections in residual learning are discussed. Finally, we summarize seminal papers, source code, models, and datasets that utilize skip connections in computer vision, including image classification, object detection, semantic segmentation, and image reconstruction. We hope this survey could inspire peer researchers in the community to develop further skip connections in various forms and tasks and the theory of residual learning in deep neural networks. The project page can be found at https://github.com/apple1986/Residual_Learning_For_Images

Graphic Design with Large Multimodal Model

In the field of graphic design, automating the integration of design elements into a cohesive multi-layered artwork not only boosts productivity but also paves the way for the democratization of graphic design. One existing practice is Graphic Layout Generation (GLG), which aims to layout sequential design elements. It has been constrained by the necessity for a predefined correct sequence of layers, thus limiting creative potential and increasing user workload. In this paper, we present Hierarchical Layout Generation (HLG) as a more flexible and pragmatic setup, which creates graphic composition from unordered sets of design elements. To tackle the HLG task, we introduce Graphist, the first layout generation model based on large multimodal models. Graphist efficiently reframes the HLG as a sequence generation problem, utilizing RGB-A images as input, outputs a JSON draft protocol, indicating the coordinates, size, and order of each element. We develop new evaluation metrics for HLG. Graphist outperforms prior arts and establishes a strong baseline for this field. Project homepage: https://github.com/graphic-design-ai/graphist

DiffI2I: Efficient Diffusion Model for Image-to-Image Translation

The Diffusion Model (DM) has emerged as the SOTA approach for image synthesis. However, the existing DM cannot perform well on some image-to-image translation (I2I) tasks. Different from image synthesis, some I2I tasks, such as super-resolution, require generating results in accordance with GT images. Traditional DMs for image synthesis require extensive iterations and large denoising models to estimate entire images, which gives their strong generative ability but also leads to artifacts and inefficiency for I2I. To tackle this challenge, we propose a simple, efficient, and powerful DM framework for I2I, called DiffI2I. Specifically, DiffI2I comprises three key components: a compact I2I prior extraction network (CPEN), a dynamic I2I transformer (DI2Iformer), and a denoising network. We train DiffI2I in two stages: pretraining and DM training. For pretraining, GT and input images are fed into CPEN$_{S1}$ to capture a compact I2I prior representation (IPR) guiding DI2Iformer. In the second stage, the DM is trained to only use the input images to estimate the same IRP as CPEN$_{S1}$. Compared to traditional DMs, the compact IPR enables DiffI2I to obtain more accurate outcomes and employ a lighter denoising network and fewer iterations. Through extensive experiments on various I2I tasks, we demonstrate that DiffI2I achieves SOTA performance while significantly reducing computational burdens.

End-to-End Out-of-distribution Detection with Self-supervised Sampling

Out-of-distribution (OOD) detection empowers the model trained on the closed set to identify unknown data in the open world. Though many prior techniques have yielded considerable improvements, two crucial obstacles still remain. Firstly, a unified perspective has yet to be presented to view the developed arts with individual designs, which is vital for providing insights into the related directions. Secondly, most research focuses on the post-processing schemes of the pre-trained features while disregarding the superiority of end-to-end training, dramatically limiting the upper bound of OOD detection. To tackle these issues, we propose a general probabilistic framework to interpret many existing methods and an OOD-data-free model, namely Self-supervised Sampling for OOD Detection (SSOD), to unfold the potential of end-to-end learning. SSOD efficiently exploits natural OOD signals from the in-distribution (ID) data based on the local property of convolution. With these supervisions, it jointly optimizes the OOD detection and conventional ID classification. Extensive experiments reveal that SSOD establishes competitive state-of-the-art performance on many large-scale benchmarks, where it outperforms the most recent approaches, such as KNN, by a large margin, e.g., 48.99% to 35.52% on SUN at FPR95.

DiffIR: Efficient Diffusion Model for Image Restoration

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis generating each pixel from scratch, most pixels of image restoration (IR) are given. Thus, for IR, traditional DMs running massive iterations on a large model to estimate whole images or feature maps is inefficient. To address this issue, we propose an efficient DM for IR (DiffIR), which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising network. Specifically, DiffIR has two training stages: pretraining and training DM. In pretraining, we input ground-truth images into CPEN$_{S1}$ to capture a compact IR prior representation (IPR) to guide DIRformer. In the second stage, we train the DM to directly estimate the same IRP as pretrained CPEN$_{S1}$ only using LQ images. We observe that since the IPR is only a compact vector, DiffIR can use fewer iterations than traditional DM to obtain accurate estimations and generate more stable and realistic results. Since the iterations are few, our DiffIR can adopt a joint optimization of CPEN$_{S2}$, DIRformer, and denoising network, which can further reduce the estimation error influence. We conduct extensive experiments on several IR tasks and achieve SOTA performance while consuming less computational costs.

Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring

Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning in the video domain. In this paper, based on the CLIP model, we revisit temporal modeling in the context of image-to-video knowledge transferring, which is the key point for extending image-text pretrained models to the video domain. We find that current temporal modeling mechanisms are tailored to either high-level semantic-dominant tasks (e.g., retrieval) or low-level visual pattern-dominant tasks (e.g., recognition), and fail to work on the two cases simultaneously. The key difficulty lies in modeling temporal dependency while taking advantage of both high-level and low-level knowledge in CLIP model. To tackle this problem, we present Spatial-Temporal Auxiliary Network (STAN) -- a simple and effective temporal modeling mechanism extending CLIP model to diverse video tasks. Specifically, to realize both low-level and high-level knowledge transferring, STAN adopts a branch structure with decomposed spatial-temporal modules that enable multi-level CLIP features to be spatial-temporally contextualized. We evaluate our method on two representative video tasks: Video-Text Retrieval and Video Recognition. Extensive experiments demonstrate the superiority of our model over the state-of-the-art methods on various datasets, including MSR-VTT, DiDeMo, LSMDC, MSVD, Kinetics-400, and Something-Something-V2. Codes will be available at https://github.com/farewellthree/STAN

Class Prototype-based Cleaner for Label Noise Learning

Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an unlabeled set for noise data. Typically, the cleaner is obtained via fitting a mixture model to the distribution of per-sample training losses. However, the modeling procedure is \emph{class agnostic} and assumes the loss distributions of clean and noise samples are the same across different classes. Unfortunately, in practice, such an assumption does not always hold due to the varying learning difficulty of different classes, thus leading to sub-optimal label noise partition criteria. In this work, we reveal this long-ignored problem and propose a simple yet effective solution, named \textbf{C}lass \textbf{P}rototype-based label noise \textbf{C}leaner (\textbf{CPC}). Unlike previous works treating all the classes equally, CPC fully considers loss distribution heterogeneity and applies class-aware modulation to partition the clean and noise data. CPC takes advantage of loss distribution modeling and intra-class consistency regularization in feature space simultaneously and thus can better distinguish clean and noise labels. We theoretically justify the effectiveness of our method by explaining it from the Expectation-Maximization (EM) framework. Extensive experiments are conducted on the noisy-label benchmarks CIFAR-10, CIFAR-100, Clothing1M and WebVision. The results show that CPC consistently brings about performance improvement across all benchmarks. Codes and pre-trained models will be released at \url{https://github.com/hjjpku/CPC.git}.

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme named as CLIP-GEN for general text-to-image generation with the language-image priors extracted with a pre-trained CLIP model. In our approach, we only require a set of unlabeled images in the general domain to train a text-to-image generator. Specifically, given an image without text labels, we first extract the embedding of the image in the united language-vision embedding space with the image encoder of CLIP. Next, we convert the image into a sequence of discrete tokens in the VQGAN codebook space (the VQGAN model can be trained with the unlabeled image dataset in hand). Finally, we train an autoregressive transformer that maps the image tokens from its unified language-vision representation. Once trained, the transformer can generate coherent image tokens based on the text embedding extracted from the text encoder of CLIP upon an input text. Such a strategy enables us to train a strong and general text-to-image generator with large text-free image dataset such as ImageNet. Qualitative and quantitative evaluations verify that our method significantly outperforms optimization-based text-to-image methods in terms of image quality while not compromising the text-image matching. Our method can even achieve comparable performance as flagship supervised models like CogView.