相关论文: 3D CoCa: Contrastive Learners are 3D Captioners

We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built on PE, PE-AV makes several key contributions to extend representations to audio,…

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt…

Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training…

Reconstructing and understanding 3D scenes from unposed sparse views in a feed-forward manner remains as a challenging task in 3D computer vision. Recent approaches use per-pixel 3D Gaussian Splatting for reconstruction, followed by a…

News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence…

Contrastive learning demonstrates great promise for representation learning. Data augmentations play a critical role in contrastive learning by providing informative views of the data without necessitating explicit labels. Nonetheless, the…

Embodied navigation demands comprehensive scene understanding and precise spatial reasoning. While image-text models excel at interpreting pixel-level color and lighting cues, 3D-text models capture volumetric structure and spatial…

CLIP achieves strong zero-shot image-text retrieval by aligning global vision and text representations, yet it falls behind on fine-grained tasks even when fine-tuned on long, detailed captions. In this work, we propose $\beta$-CLIP, a…

Contrastive learning methods in self-supervised settings have primarily focused on pre-training encoders, while decoders are typically introduced and trained separately for downstream dense prediction tasks. However, this conventional…

An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…

Self-supervised representation learning is a critical problem in computer vision, as it provides a way to pretrain feature extractors on large unlabeled datasets that can be used as an initialization for more efficient and effective…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of…

The 3D contrastive learning paradigm has demonstrated remarkable performance in downstream tasks through pretraining on point cloud data. Recent advances involve additional 2D image priors associated with 3D point clouds for further…

State-of-the-art (SOTA) image and text generation models are multimodal models that have many similarities to large language models (LLMs). Despite achieving strong performances, leading foundational multimodal model architectures…

Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some…

Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an…

3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part…

Self-Supervised Learning (SSL) has demonstrated promising results in 3D medical image analysis. However, the lack of high-level semantics in pre-training still heavily hinders the performance of downstream tasks. We observe that 3D medical…

Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns. In this paper, we…