Related papers: SGDiff: Scene Graph Guided Diffusion Model for Ima…
We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…
Recent advances in generative modeling with diffusion processes (DPs) enabled breakthroughs in image synthesis. Despite impressive image quality, these models have various prompt compliance problems, including low recall in generating…
In controllable generation tasks, flexibly manipulating the generated images to attain a desired appearance or structure based on a single input image cue remains a critical and longstanding challenge. Achieving this requires the effective…
Image paragraph captioning aims to describe a given image with a sequence of coherent sentences. Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences.…
The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt…
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…
Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…
Recent text-driven image editing in diffusion models has shown remarkable success. However, the existing methods assume that the user's description sufficiently grounds the contexts in the source image, such as objects, background, style,…
Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses…
Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often…
Diffusion models have demonstrated excellent performance in image generation. Although various few-shot semantic segmentation (FSS) models with different network structures have been proposed, performance improvement has reached a…
Answering complex questions about images is an ambitious goal for machine intelligence, which requires a joint understanding of images, text, and commonsense knowledge, as well as a strong reasoning ability. Recently, multimodal…
Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to…
Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting…
Visual Foundation Models (VFMs) such as the Segment Anything Model (SAM) have significantly advanced broad use of image segmentation. However, SAM and its variants necessitate substantial manual effort for prompt generation and additional…
We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation. We tackle this problem differently by formulating the task as an image translation problem steered by text and motion magnitude prompts, as shown in…
Recent years have witnessed astonishing advances in the field of multimodal representation learning, with contrastive learning being the cornerstone for major breakthroughs. Latest works delivered further improvements by incorporating…
We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocations…
The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image…